< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 74 in Layer 25

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.5817. Min Act: -0.1700

Data Index: 3166497 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.5505. Min Act: -0.1700

Data Index: 5306403 (Open Web Text)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.5505. Min Act: -0.1700

Data Index: 5092983 (Open Web Text)

Max Activating Token Index: 873

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.4880. Min Act: -0.1700

Data Index: 4041733 (Open Web Text)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.4880. Min Act: -0.1700

Data Index: 3457682 (Open Web Text)

Max Activating Token Index: 655

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3942. Min Act: -0.1700

Data Index: 3248619 (Open Web Text)

Max Activating Token Index: 177

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3942. Min Act: -0.1700

Data Index: 1341441 (Open Web Text)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3942. Min Act: -0.1700

Data Index: 5101628 (Open Web Text)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3630. Min Act: -0.1700

Data Index: 2489982 (Open Web Text)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3317. Min Act: -0.1700

Data Index: 4504114 (Open Web Text)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3630. Min Act: -0.1700

Data Index: 6215493 (Open Web Text)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3005. Min Act: -0.1700

Data Index: 3067277 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.3005. Min Act: -0.1700

Data Index: 8643090 (Open Web Text)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.2380. Min Act: -0.1700

Data Index: 7952434 (Open Web Text)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.2380. Min Act: -0.1700

Data Index: 7284075 (Open Web Text)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.2380. Min Act: -0.1700

Data Index: 3322870 (Open Web Text)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.2067. Min Act: -0.1700

Data Index: 1381094 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.2380. Min Act: -0.1700

Data Index: 1123339 (Open Web Text)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.2067. Min Act: -0.1700

Data Index: 7428961 (Open Web Text)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.5817. Min Range: -6.5817

Max Act: 6.2067. Min Act: -0.1700

Data Index: 7594856 (Open Web Text)

Max Activating Token Index: 474

Click toggle to see full text

Truncated

Full Text #19