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

Dataset: Open Web Text

Neuron 1997 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: 1.8207. Min Range: -1.8207

Max Act: 1.8207. Min Act: -0.1700

Data Index: 2388699 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.8132. Min Act: -0.1700

Data Index: 4490036 (Open Web Text)

Max Activating Token Index: 683

Text #2

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7929. Min Act: -0.1700

Data Index: 7826683 (Open Web Text)

Max Activating Token Index: 26

Text #3

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7841. Min Act: -0.1698

Data Index: 2736630 (Open Web Text)

Max Activating Token Index: 753

Text #4

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7860. Min Act: -0.1694

Data Index: 2373074 (Open Web Text)

Max Activating Token Index: 1023

Text #5

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7770. Min Act: -0.1700

Data Index: 7755717 (Open Web Text)

Max Activating Token Index: 507

Text #6

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7613. Min Act: -0.1700

Data Index: 6718386 (Open Web Text)

Max Activating Token Index: 451

Text #7

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7712. Min Act: -0.1700

Data Index: 5118331 (Open Web Text)

Max Activating Token Index: 624

Text #8

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7680. Min Act: -0.1700

Data Index: 2044748 (Open Web Text)

Max Activating Token Index: 1023

Text #9

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7655. Min Act: -0.1700

Data Index: 7580264 (Open Web Text)

Max Activating Token Index: 436

Text #10

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7603. Min Act: -0.1700

Data Index: 8324900 (Open Web Text)

Max Activating Token Index: 772

Text #11

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7596. Min Act: -0.1700

Data Index: 6983185 (Open Web Text)

Max Activating Token Index: 960

Text #12

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7536. Min Act: -0.1700

Data Index: 2397093 (Open Web Text)

Max Activating Token Index: 839

Text #13

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7498. Min Act: -0.1700

Data Index: 3408241 (Open Web Text)

Max Activating Token Index: 584

Text #14

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7503. Min Act: -0.1700

Data Index: 104971 (Open Web Text)

Max Activating Token Index: 593

Text #15

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7580. Min Act: -0.1700

Data Index: 1475001 (Open Web Text)

Max Activating Token Index: 65

Text #16

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7468. Min Act: -0.1700

Data Index: 5606651 (Open Web Text)

Max Activating Token Index: 335

Text #17

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7498. Min Act: -0.1697

Data Index: 6018053 (Open Web Text)

Max Activating Token Index: 758

Text #18

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7540. Min Act: -0.1698

Data Index: 1180514 (Open Web Text)

Max Activating Token Index: 954

Text #19

Max Range: 1.8207. Min Range: -1.8207

Max Act: 1.7432. Min Act: -0.1700

Data Index: 6101166 (Open Web Text)

Max Activating Token Index: 352