< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 6349 in Layer 39

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 10.0798. Min Range: -10.0798

Max Act: 10.0798. Min Act: -0.1700

Data Index: 930782 (Open Web Text)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.9548. Min Act: -0.1700

Data Index: 1424379 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.8298. Min Act: -0.1700

Data Index: 3123126 (Open Web Text)

Max Activating Token Index: 545

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.8298. Min Act: -0.1700

Data Index: 7425615 (Open Web Text)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.7048. Min Act: -0.1700

Data Index: 1457448 (Open Web Text)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.7048. Min Act: -0.1700

Data Index: 5796807 (Open Web Text)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.5798. Min Act: -0.1700

Data Index: 437167 (Open Web Text)

Max Activating Token Index: 784

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.5173. Min Act: -0.1700

Data Index: 445313 (Open Web Text)

Max Activating Token Index: 443

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.5173. Min Act: -0.1700

Data Index: 5124027 (Open Web Text)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.5173. Min Act: -0.1700

Data Index: 5429678 (Open Web Text)

Max Activating Token Index: 383

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.4548. Min Act: -0.1700

Data Index: 3137068 (Open Web Text)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.3923. Min Act: -0.1700

Data Index: 8037784 (Open Web Text)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.3923. Min Act: -0.1700

Data Index: 5613820 (Open Web Text)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.3298. Min Act: -0.1700

Data Index: 3962153 (Open Web Text)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.3298. Min Act: -0.1700

Data Index: 4651431 (Open Web Text)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.2673. Min Act: -0.1700

Data Index: 4120933 (Open Web Text)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.2673. Min Act: -0.1700

Data Index: 7317799 (Open Web Text)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.2673. Min Act: -0.1700

Data Index: 2345380 (Open Web Text)

Max Activating Token Index: 536

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.2673. Min Act: -0.1700

Data Index: 3555222 (Open Web Text)

Max Activating Token Index: 549

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 10.0798. Min Range: -10.0798

Max Act: 9.2673. Min Act: -0.1700

Data Index: 3767604 (Open Web Text)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #19