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

Dataset: Open Web Text

Neuron 939 in Layer 2

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: 4.6139. Min Range: -4.6139

Max Act: 4.6139. Min Act: -0.1700

Data Index: 3402594 (Open Web Text)

Max Activating Token Index: 364

Text #1

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.5972. Min Act: -0.1700

Data Index: 8727327 (Open Web Text)

Max Activating Token Index: 52

Text #2

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.5616. Min Act: -0.1700

Data Index: 489364 (Open Web Text)

Max Activating Token Index: 622

Text #3

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.5343. Min Act: -0.1700

Data Index: 6597802 (Open Web Text)

Max Activating Token Index: 263

Text #4

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.5237. Min Act: -0.1700

Data Index: 6638729 (Open Web Text)

Max Activating Token Index: 274

Text #5

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4881. Min Act: -0.1700

Data Index: 6123529 (Open Web Text)

Max Activating Token Index: 460

Text #6

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.5089. Min Act: -0.1700

Data Index: 8312479 (Open Web Text)

Max Activating Token Index: 532

Text #7

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4943. Min Act: -0.1700

Data Index: 8362292 (Open Web Text)

Max Activating Token Index: 365

Text #8

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.5072. Min Act: -0.1700

Data Index: 5426959 (Open Web Text)

Max Activating Token Index: 617

Text #9

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4718. Min Act: -0.1700

Data Index: 8558329 (Open Web Text)

Max Activating Token Index: 268

Text #10

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4372. Min Act: -0.1700

Data Index: 6413784 (Open Web Text)

Max Activating Token Index: 492

Text #11

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4239. Min Act: -0.1700

Data Index: 3613908 (Open Web Text)

Max Activating Token Index: 381

Text #12

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4246. Min Act: -0.1700

Data Index: 1049540 (Open Web Text)

Max Activating Token Index: 854

Text #13

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4541. Min Act: -0.1700

Data Index: 1036057 (Open Web Text)

Max Activating Token Index: 580

Text #14

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4383. Min Act: -0.1700

Data Index: 4361673 (Open Web Text)

Max Activating Token Index: 574

Text #15

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4266. Min Act: -0.1700

Data Index: 8008933 (Open Web Text)

Max Activating Token Index: 534

Text #16

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4302. Min Act: -0.1700

Data Index: 1334482 (Open Web Text)

Max Activating Token Index: 807

Text #17

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4271. Min Act: -0.1700

Data Index: 1896935 (Open Web Text)

Max Activating Token Index: 644

Text #18

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4012. Min Act: -0.1700

Data Index: 1075531 (Open Web Text)

Max Activating Token Index: 816

Text #19

Max Range: 4.6139. Min Range: -4.6139

Max Act: 4.4209. Min Act: -0.1700

Data Index: 777570 (Open Web Text)

Max Activating Token Index: 429