< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 1175 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.3464. Min Act: -0.1700

Data Index: 2805066 (Open Web Text)

Max Activating Token Index: 880

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.2640. Min Act: -0.1695

Data Index: 7272698 (Open Web Text)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.2214. Min Act: -0.1699

Data Index: 6721995 (Open Web Text)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.2224. Min Act: -0.1700

Data Index: 128200 (Open Web Text)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.2064. Min Act: -0.1700

Data Index: 2650026 (Open Web Text)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.2123. Min Act: -0.1700

Data Index: 3290808 (Open Web Text)

Max Activating Token Index: 335

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1936. Min Act: -0.1700

Data Index: 5252253 (Open Web Text)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1750. Min Act: -0.1700

Data Index: 4776764 (Open Web Text)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1906. Min Act: -0.1700

Data Index: 1060971 (Open Web Text)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1920. Min Act: -0.1682

Data Index: 816036 (Open Web Text)

Max Activating Token Index: 118

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1796. Min Act: -0.1700

Data Index: 824259 (Open Web Text)

Max Activating Token Index: 665

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1902. Min Act: -0.1700

Data Index: 1561864 (Open Web Text)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1601. Min Act: -0.1700

Data Index: 3099468 (Open Web Text)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1681. Min Act: -0.1700

Data Index: 5754652 (Open Web Text)

Max Activating Token Index: 359

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1509. Min Act: -0.1700

Data Index: 5783818 (Open Web Text)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1687. Min Act: -0.1700

Data Index: 1503475 (Open Web Text)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1524. Min Act: -0.1699

Data Index: 4780320 (Open Web Text)

Max Activating Token Index: 553

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1582. Min Act: -0.1700

Data Index: 804571 (Open Web Text)

Max Activating Token Index: 519

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1493. Min Act: -0.1700

Data Index: 775102 (Open Web Text)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.3464. Min Range: -2.3464

Max Act: 2.1471. Min Act: -0.1700

Data Index: 140964 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #19