Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 3 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.5828. Min Act: -0.1700

Data Index: 174356 (C4 (Web Text))

Max Activating Token Index: 332

Text #1

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.5828. Min Act: -0.1700

Data Index: 1196626 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.5045. Min Act: -0.1700

Data Index: 529674 (C4 (Web Text))

Max Activating Token Index: 676

Text #3

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.5358. Min Act: -0.1700

Data Index: 59455 (C4 (Web Text))

Max Activating Token Index: 330

Text #4

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.5202. Min Act: -0.1700

Data Index: 245436 (C4 (Web Text))

Max Activating Token Index: 254

Text #5

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.5202. Min Act: -0.1700

Data Index: 374878 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4888. Min Act: -0.1700

Data Index: 315515 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.5045. Min Act: -0.1700

Data Index: 867340 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4575. Min Act: -0.1700

Data Index: 40707 (C4 (Web Text))

Max Activating Token Index: 600

Text #9

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4732. Min Act: -0.1700

Data Index: 1323840 (C4 (Web Text))

Max Activating Token Index: 700

Text #10

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4575. Min Act: -0.1700

Data Index: 1279262 (C4 (Web Text))

Max Activating Token Index: 391

Text #11

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4732. Min Act: -0.1700

Data Index: 317724 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4418. Min Act: -0.1700

Data Index: 344124 (C4 (Web Text))

Max Activating Token Index: 509

Text #13

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4575. Min Act: -0.1700

Data Index: 975663 (C4 (Web Text))

Max Activating Token Index: 667

Text #14

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4732. Min Act: -0.1700

Data Index: 705760 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4732. Min Act: -0.1700

Data Index: 1264438 (C4 (Web Text))

Max Activating Token Index: 443

Text #16

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4575. Min Act: -0.1700

Data Index: 67406 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4418. Min Act: -0.1700

Data Index: 174410 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4575. Min Act: -0.1700

Data Index: 277643 (C4 (Web Text))

Max Activating Token Index: 221

Text #19

Max Range: 3.5828. Min Range: -3.5828

Max Act: 3.4575. Min Act: -0.1700

Data Index: 57233 (C4 (Web Text))

Max Activating Token Index: 672