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

Dataset: Open Web Text

Neuron 972 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')

Text #0

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.1948. Min Act: -0.1700

Data Index: 443382 (Open Web Text)

Max Activating Token Index: 664

Text #1

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.1369. Min Act: -0.1700

Data Index: 526001 (Open Web Text)

Max Activating Token Index: 982

Text #2

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0938. Min Act: -0.1700

Data Index: 826173 (Open Web Text)

Max Activating Token Index: 66

Text #3

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0545. Min Act: -0.1700

Data Index: 7043432 (Open Web Text)

Max Activating Token Index: 688

Text #4

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0266. Min Act: -0.1700

Data Index: 5933514 (Open Web Text)

Max Activating Token Index: 561

Text #5

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0298. Min Act: -0.1700

Data Index: 757186 (Open Web Text)

Max Activating Token Index: 493

Text #6

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0308. Min Act: -0.1700

Data Index: 8581011 (Open Web Text)

Max Activating Token Index: 439

Text #7

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0070. Min Act: -0.1700

Data Index: 725907 (Open Web Text)

Max Activating Token Index: 359

Text #8

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0222. Min Act: -0.1700

Data Index: 8418826 (Open Web Text)

Max Activating Token Index: 164

Text #9

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0219. Min Act: -0.1700

Data Index: 4344124 (Open Web Text)

Max Activating Token Index: 905

Text #10

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9881. Min Act: -0.1700

Data Index: 898844 (Open Web Text)

Max Activating Token Index: 838

Text #11

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9885. Min Act: -0.1700

Data Index: 8778626 (Open Web Text)

Max Activating Token Index: 185

Text #12

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0135. Min Act: -0.1700

Data Index: 2672761 (Open Web Text)

Max Activating Token Index: 341

Text #13

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0118. Min Act: -0.1700

Data Index: 339181 (Open Web Text)

Max Activating Token Index: 488

Text #14

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0256. Min Act: -0.1700

Data Index: 8189899 (Open Web Text)

Max Activating Token Index: 484

Text #15

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0036. Min Act: -0.1700

Data Index: 7052326 (Open Web Text)

Max Activating Token Index: 102

Text #16

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9896. Min Act: -0.1700

Data Index: 984434 (Open Web Text)

Max Activating Token Index: 648

Text #17

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9749. Min Act: -0.1700

Data Index: 6019498 (Open Web Text)

Max Activating Token Index: 357

Text #18

Max Range: 5.1948. Min Range: -5.1948

Max Act: 4.9824. Min Act: -0.1700

Data Index: 3463860 (Open Web Text)

Max Activating Token Index: 217

Text #19

Max Range: 5.1948. Min Range: -5.1948

Max Act: 5.0079. Min Act: -0.1700

Data Index: 5696712 (Open Web Text)

Max Activating Token Index: 837