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

Dataset: Open Web Text

Neuron 553 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: 1.4628. Min Range: -1.4628

Max Act: 1.4628. Min Act: -0.1700

Data Index: 1724698 (Open Web Text)

Max Activating Token Index: 659

Text #1

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4351. Min Act: -0.1700

Data Index: 875353 (Open Web Text)

Max Activating Token Index: 70

Text #2

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4378. Min Act: -0.1700

Data Index: 2049525 (Open Web Text)

Max Activating Token Index: 118

Text #3

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4248. Min Act: -0.1700

Data Index: 7721437 (Open Web Text)

Max Activating Token Index: 172

Text #4

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4108. Min Act: -0.1700

Data Index: 1754461 (Open Web Text)

Max Activating Token Index: 250

Text #5

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4164. Min Act: -0.1700

Data Index: 2352579 (Open Web Text)

Max Activating Token Index: 753

Text #6

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4176. Min Act: -0.1700

Data Index: 5237167 (Open Web Text)

Max Activating Token Index: 488

Text #7

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4206. Min Act: -0.1700

Data Index: 2772859 (Open Web Text)

Max Activating Token Index: 105

Text #8

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4129. Min Act: -0.1700

Data Index: 7316335 (Open Web Text)

Max Activating Token Index: 399

Text #9

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4046. Min Act: -0.1700

Data Index: 2193748 (Open Web Text)

Max Activating Token Index: 538

Text #10

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3997. Min Act: -0.1700

Data Index: 5695744 (Open Web Text)

Max Activating Token Index: 216

Text #11

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4042. Min Act: -0.1700

Data Index: 2667545 (Open Web Text)

Max Activating Token Index: 535

Text #12

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4024. Min Act: -0.1700

Data Index: 8643039 (Open Web Text)

Max Activating Token Index: 330

Text #13

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4031. Min Act: -0.1700

Data Index: 8237435 (Open Web Text)

Max Activating Token Index: 621

Text #14

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.4068. Min Act: -0.1700

Data Index: 7409613 (Open Web Text)

Max Activating Token Index: 569

Text #15

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3921. Min Act: -0.1700

Data Index: 2949383 (Open Web Text)

Max Activating Token Index: 219

Text #16

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3941. Min Act: -0.1700

Data Index: 3948094 (Open Web Text)

Max Activating Token Index: 598

Text #17

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3856. Min Act: -0.1700

Data Index: 3180476 (Open Web Text)

Max Activating Token Index: 34

Text #18

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3896. Min Act: -0.1700

Data Index: 2742692 (Open Web Text)

Max Activating Token Index: 98

Text #19

Max Range: 1.4628. Min Range: -1.4628

Max Act: 1.3919. Min Act: -0.1700

Data Index: 122866 (Open Web Text)

Max Activating Token Index: 230