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

Dataset: Open Web Text

Neuron 1034 in Layer 6

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: 4.1586. Min Range: -4.1586

Max Act: 4.1586. Min Act: -0.1700

Data Index: 7749299 (Open Web Text)

Max Activating Token Index: 764

Text #1

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.1227. Min Act: -0.1700

Data Index: 236366 (Open Web Text)

Max Activating Token Index: 490

Text #2

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0730. Min Act: -0.1700

Data Index: 3393229 (Open Web Text)

Max Activating Token Index: 584

Text #3

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0696. Min Act: -0.1700

Data Index: 3303880 (Open Web Text)

Max Activating Token Index: 882

Text #4

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0278. Min Act: -0.1700

Data Index: 1222201 (Open Web Text)

Max Activating Token Index: 433

Text #5

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0737. Min Act: -0.1700

Data Index: 6865129 (Open Web Text)

Max Activating Token Index: 16

Text #6

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0784. Min Act: -0.1700

Data Index: 7565632 (Open Web Text)

Max Activating Token Index: 92

Text #7

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0531. Min Act: -0.1700

Data Index: 8763340 (Open Web Text)

Max Activating Token Index: 157

Text #8

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0404. Min Act: -0.1700

Data Index: 3136407 (Open Web Text)

Max Activating Token Index: 1007

Text #9

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0402. Min Act: -0.1700

Data Index: 7976660 (Open Web Text)

Max Activating Token Index: 550

Text #10

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0362. Min Act: -0.1700

Data Index: 27327 (Open Web Text)

Max Activating Token Index: 1012

Text #11

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0030. Min Act: -0.1700

Data Index: 5542342 (Open Web Text)

Max Activating Token Index: 212

Text #12

Max Range: 4.1586. Min Range: -4.1586

Max Act: 4.0096. Min Act: -0.1700

Data Index: 7619723 (Open Web Text)

Max Activating Token Index: 267

Text #13

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.9854. Min Act: -0.1700

Data Index: 6819096 (Open Web Text)

Max Activating Token Index: 705

Text #14

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.9635. Min Act: -0.1700

Data Index: 746872 (Open Web Text)

Max Activating Token Index: 301

Text #15

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.9379. Min Act: -0.1700

Data Index: 735451 (Open Web Text)

Max Activating Token Index: 568

Text #16

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.9539. Min Act: -0.1700

Data Index: 2796778 (Open Web Text)

Max Activating Token Index: 195

Text #17

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.9748. Min Act: -0.1700

Data Index: 8583041 (Open Web Text)

Max Activating Token Index: 499

Text #18

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.9625. Min Act: -0.1700

Data Index: 7163205 (Open Web Text)

Max Activating Token Index: 869

Text #19

Max Range: 4.1586. Min Range: -4.1586

Max Act: 3.9602. Min Act: -0.1700

Data Index: 3327718 (Open Web Text)

Max Activating Token Index: 972