Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 2831 in Layer 43

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.3442. Min Act: -0.1700

Data Index: 649885 (Open Web Text)

Max Activating Token Index: 848

Text #1

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.2504. Min Act: -0.1700

Data Index: 488674 (Open Web Text)

Max Activating Token Index: 371

Text #2

Max Range: 7.3442. Min Range: -7.3442

Max Act: 7.0942. Min Act: -0.1700

Data Index: 2175777 (Open Web Text)

Max Activating Token Index: 831

Text #3

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.9379. Min Act: -0.1700

Data Index: 1280813 (Open Web Text)

Max Activating Token Index: 54

Text #4

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.9379. Min Act: -0.1700

Data Index: 1262699 (Open Web Text)

Max Activating Token Index: 931

Text #5

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.9067. Min Act: -0.1700

Data Index: 3326267 (Open Web Text)

Max Activating Token Index: 824

Text #6

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.9067. Min Act: -0.1700

Data Index: 1127885 (Open Web Text)

Max Activating Token Index: 605

Text #7

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.9067. Min Act: -0.1700

Data Index: 4187597 (Open Web Text)

Max Activating Token Index: 253

Text #8

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.8442. Min Act: -0.1700

Data Index: 4964408 (Open Web Text)

Max Activating Token Index: 938

Text #9

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.8129. Min Act: -0.1700

Data Index: 172224 (Open Web Text)

Max Activating Token Index: 58

Text #10

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.7817. Min Act: -0.1700

Data Index: 7786849 (Open Web Text)

Max Activating Token Index: 332

Text #11

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.7817. Min Act: -0.1700

Data Index: 6223916 (Open Web Text)

Max Activating Token Index: 644

Text #12

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.7504. Min Act: -0.1700

Data Index: 587233 (Open Web Text)

Max Activating Token Index: 106

Text #13

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.7504. Min Act: -0.1700

Data Index: 6067177 (Open Web Text)

Max Activating Token Index: 360

Text #14

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.7504. Min Act: -0.1700

Data Index: 8528410 (Open Web Text)

Max Activating Token Index: 369

Text #15

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.6879. Min Act: -0.1700

Data Index: 5296419 (Open Web Text)

Max Activating Token Index: 747

Text #16

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.6879. Min Act: -0.1700

Data Index: 3636315 (Open Web Text)

Max Activating Token Index: 258

Text #17

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.6879. Min Act: -0.1700

Data Index: 2106553 (Open Web Text)

Max Activating Token Index: 322

Text #18

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.6567. Min Act: -0.1700

Data Index: 4815171 (Open Web Text)

Max Activating Token Index: 127

Text #19

Max Range: 7.3442. Min Range: -7.3442

Max Act: 6.5942. Min Act: -0.1700

Data Index: 5210193 (Open Web Text)

Max Activating Token Index: 746