< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.9798. Min Act: -0.1700

Data Index: 6306089 (Open Web Text)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.9141. Min Act: -0.1700

Data Index: 1345734 (Open Web Text)

Max Activating Token Index: 723

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8756. Min Act: -0.1700

Data Index: 572640 (Open Web Text)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8920. Min Act: -0.1700

Data Index: 6949087 (Open Web Text)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8580. Min Act: -0.1700

Data Index: 1729791 (Open Web Text)

Max Activating Token Index: 313

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8664. Min Act: -0.1700

Data Index: 3612139 (Open Web Text)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8750. Min Act: -0.1700

Data Index: 983839 (Open Web Text)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8707. Min Act: -0.1700

Data Index: 301493 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8503. Min Act: -0.1700

Data Index: 3499407 (Open Web Text)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8442. Min Act: -0.1700

Data Index: 3146128 (Open Web Text)

Max Activating Token Index: 529

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8602. Min Act: -0.1700

Data Index: 7715607 (Open Web Text)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8579. Min Act: -0.1700

Data Index: 8282733 (Open Web Text)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8426. Min Act: -0.1700

Data Index: 4943974 (Open Web Text)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8419. Min Act: -0.1700

Data Index: 2617063 (Open Web Text)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8246. Min Act: -0.1700

Data Index: 7809415 (Open Web Text)

Max Activating Token Index: 859

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.7927. Min Act: -0.1700

Data Index: 6526575 (Open Web Text)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8153. Min Act: -0.1700

Data Index: 795769 (Open Web Text)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.7954. Min Act: -0.1700

Data Index: 4560916 (Open Web Text)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.8051. Min Act: -0.1700

Data Index: 8242038 (Open Web Text)

Max Activating Token Index: 146

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.9798. Min Range: -2.9798

Max Act: 2.7989. Min Act: -0.1700

Data Index: 4122466 (Open Web Text)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #19