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

Dataset: Open Web Text

Neuron 142 in Layer 0

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: 1.7779. Min Range: -1.7779

Max Act: 1.7779. Min Act: -0.0934

Data Index: 4113911 (Open Web Text)

Max Activating Token Index: 83

Text #1

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7696. Min Act: -0.0469

Data Index: 3566960 (Open Web Text)

Max Activating Token Index: 362

Text #2

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7646. Min Act: -0.0469

Data Index: 4674498 (Open Web Text)

Max Activating Token Index: 675

Text #3

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7351. Min Act: -0.1065

Data Index: 8032708 (Open Web Text)

Max Activating Token Index: 418

Text #4

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7311. Min Act: -0.0469

Data Index: 6340744 (Open Web Text)

Max Activating Token Index: 695

Text #5

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7331. Min Act: -0.0751

Data Index: 2543510 (Open Web Text)

Max Activating Token Index: 508

Text #6

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7214. Min Act: -0.0506

Data Index: 6281434 (Open Web Text)

Max Activating Token Index: 814

Text #7

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7314. Min Act: -0.0469

Data Index: 6497409 (Open Web Text)

Max Activating Token Index: 378

Text #8

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7378. Min Act: -0.0897

Data Index: 261251 (Open Web Text)

Max Activating Token Index: 858

Text #9

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7273. Min Act: -0.0469

Data Index: 993191 (Open Web Text)

Max Activating Token Index: 430

Text #10

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7263. Min Act: -0.0519

Data Index: 6188928 (Open Web Text)

Max Activating Token Index: 948

Text #11

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7235. Min Act: -0.0952

Data Index: 2370468 (Open Web Text)

Max Activating Token Index: 336

Text #12

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7143. Min Act: -0.0469

Data Index: 1484267 (Open Web Text)

Max Activating Token Index: 486

Text #13

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7125. Min Act: -0.0469

Data Index: 6290276 (Open Web Text)

Max Activating Token Index: 961

Text #14

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7139. Min Act: -0.0469

Data Index: 2127529 (Open Web Text)

Max Activating Token Index: 435

Text #15

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7184. Min Act: -0.0469

Data Index: 4234778 (Open Web Text)

Max Activating Token Index: 757

Text #16

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7147. Min Act: -0.0469

Data Index: 1035285 (Open Web Text)

Max Activating Token Index: 992

Text #17

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7086. Min Act: -0.1189

Data Index: 5954323 (Open Web Text)

Max Activating Token Index: 803

Text #18

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7073. Min Act: -0.0469

Data Index: 3627786 (Open Web Text)

Max Activating Token Index: 356

Text #19

Max Range: 1.7779. Min Range: -1.7779

Max Act: 1.7117. Min Act: -0.1658

Data Index: 5858570 (Open Web Text)

Max Activating Token Index: 37