< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 19 in Layer 38

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.9865. Min Act: -0.1700

Data Index: 8394264 (Open Web Text)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.5490. Min Act: -0.1700

Data Index: 2873943 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.4240. Min Act: -0.1700

Data Index: 7501068 (Open Web Text)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.3615. Min Act: -0.1700

Data Index: 4257719 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.3615. Min Act: -0.1698

Data Index: 967686 (Open Web Text)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.2990. Min Act: -0.1700

Data Index: 7707443 (Open Web Text)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.3615. Min Act: -0.1700

Data Index: 6805548 (Open Web Text)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.3615. Min Act: -0.1700

Data Index: 4398897 (Open Web Text)

Max Activating Token Index: 689

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.2990. Min Act: -0.1700

Data Index: 1826283 (Open Web Text)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.2365. Min Act: -0.1700

Data Index: 5129268 (Open Web Text)

Max Activating Token Index: 46

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.2990. Min Act: -0.1700

Data Index: 2143479 (Open Web Text)

Max Activating Token Index: 675

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.2365. Min Act: -0.1700

Data Index: 5049565 (Open Web Text)

Max Activating Token Index: 886

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.2365. Min Act: -0.1700

Data Index: 596358 (Open Web Text)

Max Activating Token Index: 664

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.1115. Min Act: -0.1700

Data Index: 4661968 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.1740. Min Act: -0.1700

Data Index: 4073661 (Open Web Text)

Max Activating Token Index: 244

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.1740. Min Act: -0.1695

Data Index: 7013662 (Open Web Text)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.1740. Min Act: -0.1700

Data Index: 2732563 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.1740. Min Act: -0.1700

Data Index: 7677983 (Open Web Text)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.2365. Min Act: -0.1700

Data Index: 2657583 (Open Web Text)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.9865. Min Range: -10.9865

Max Act: 10.1740. Min Act: -0.1700

Data Index: 8154458 (Open Web Text)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #19