Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1482 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4792. Min Act: -0.1700

Data Index: 245673 (C4 (Web Text))

Max Activating Token Index: 761

Text #1

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.5417. Min Act: -0.1700

Data Index: 403219 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4479. Min Act: -0.1700

Data Index: 1054039 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3854. Min Act: -0.1700

Data Index: 726189 (C4 (Web Text))

Max Activating Token Index: 941

Text #4

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 491404 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4479. Min Act: -0.1700

Data Index: 726615 (C4 (Web Text))

Max Activating Token Index: 928

Text #6

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4479. Min Act: -0.1700

Data Index: 1049113 (C4 (Web Text))

Max Activating Token Index: 770

Text #7

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 1294636 (C4 (Web Text))

Max Activating Token Index: 738

Text #8

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 289532 (C4 (Web Text))

Max Activating Token Index: 309

Text #9

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 1099116 (C4 (Web Text))

Max Activating Token Index: 438

Text #10

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3854. Min Act: -0.1700

Data Index: 877169 (C4 (Web Text))

Max Activating Token Index: 875

Text #11

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 372746 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.4167. Min Act: -0.1700

Data Index: 905375 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.2604. Min Act: -0.1700

Data Index: 832836 (C4 (Web Text))

Max Activating Token Index: 868

Text #14

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3854. Min Act: -0.1700

Data Index: 584054 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3854. Min Act: -0.1700

Data Index: 439997 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.2917. Min Act: -0.1700

Data Index: 139223 (C4 (Web Text))

Max Activating Token Index: 592

Text #17

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 749177 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 748916 (C4 (Web Text))

Max Activating Token Index: 328

Text #19

Max Range: 5.5417. Min Range: -5.5417

Max Act: 5.3542. Min Act: -0.1700

Data Index: 504622 (C4 (Web Text))

Max Activating Token Index: 681