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

Dataset: Open Web Text

Neuron 2474 in Layer 3

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: 3.7274. Min Range: -3.7274

Max Act: 3.7274. Min Act: -0.1700

Data Index: 6899215 (Open Web Text)

Max Activating Token Index: 219

Text #1

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.6670. Min Act: -0.1700

Data Index: 4004078 (Open Web Text)

Max Activating Token Index: 672

Text #2

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.6131. Min Act: -0.1700

Data Index: 7456578 (Open Web Text)

Max Activating Token Index: 314

Text #3

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.6092. Min Act: -0.1700

Data Index: 3258116 (Open Web Text)

Max Activating Token Index: 493

Text #4

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.6150. Min Act: -0.1700

Data Index: 6169019 (Open Web Text)

Max Activating Token Index: 11

Text #5

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5930. Min Act: -0.1700

Data Index: 3820138 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.6030. Min Act: -0.1700

Data Index: 6000291 (Open Web Text)

Max Activating Token Index: 529

Text #7

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5817. Min Act: -0.1700

Data Index: 7367055 (Open Web Text)

Max Activating Token Index: 234

Text #8

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5628. Min Act: -0.1700

Data Index: 6108504 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5619. Min Act: -0.1700

Data Index: 7063358 (Open Web Text)

Max Activating Token Index: 392

Text #10

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5418. Min Act: -0.1700

Data Index: 154725 (Open Web Text)

Max Activating Token Index: 445

Text #11

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5446. Min Act: -0.1700

Data Index: 3560405 (Open Web Text)

Max Activating Token Index: 132

Text #12

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5682. Min Act: -0.1700

Data Index: 6073491 (Open Web Text)

Max Activating Token Index: 460

Text #13

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5392. Min Act: -0.1700

Data Index: 8121891 (Open Web Text)

Max Activating Token Index: 309

Text #14

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5438. Min Act: -0.1700

Data Index: 8038769 (Open Web Text)

Max Activating Token Index: 438

Text #15

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5346. Min Act: -0.1700

Data Index: 7487457 (Open Web Text)

Max Activating Token Index: 92

Text #16

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5361. Min Act: -0.1700

Data Index: 3193609 (Open Web Text)

Max Activating Token Index: 264

Text #17

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5223. Min Act: -0.1700

Data Index: 3949087 (Open Web Text)

Max Activating Token Index: 399

Text #18

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5271. Min Act: -0.1700

Data Index: 6453166 (Open Web Text)

Max Activating Token Index: 862

Text #19

Max Range: 3.7274. Min Range: -3.7274

Max Act: 3.5356. Min Act: -0.1700

Data Index: 4478085 (Open Web Text)

Max Activating Token Index: 865