Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1858 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.8189. Min Act: -0.0000

Data Index: 668110 (C4 (Web Text))

Max Activating Token Index: 246

Text #1

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.7651. Min Act: -0.0000

Data Index: 219120 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.5798. Min Act: -0.0001

Data Index: 1210021 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.6044. Min Act: -0.0001

Data Index: 714792 (C4 (Web Text))

Max Activating Token Index: 521

Text #4

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.5108. Min Act: -0.0000

Data Index: 320599 (C4 (Web Text))

Max Activating Token Index: 498

Text #5

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.5446. Min Act: -0.0000

Data Index: 444920 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3461. Min Act: -0.0001

Data Index: 343387 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1357410 (C4 (Web Text))

Max Activating Token Index: 587

Text #8

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4085. Min Act: -0.0000

Data Index: 837694 (C4 (Web Text))

Max Activating Token Index: 930

Text #9

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4610. Min Act: -0.0000

Data Index: 1135648 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3804. Min Act: -0.0000

Data Index: 507491 (C4 (Web Text))

Max Activating Token Index: 893

Text #11

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.4047. Min Act: -0.0000

Data Index: 1086150 (C4 (Web Text))

Max Activating Token Index: 208

Text #12

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3744. Min Act: -0.0000

Data Index: 229009 (C4 (Web Text))

Max Activating Token Index: 614

Text #13

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.2943. Min Act: -0.0000

Data Index: 1220249 (C4 (Web Text))

Max Activating Token Index: 468

Text #14

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3366. Min Act: -0.0000

Data Index: 1246621 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3461. Min Act: -0.0001

Data Index: 54990 (C4 (Web Text))

Max Activating Token Index: 84

Text #16

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.2871. Min Act: -0.0000

Data Index: 142886 (C4 (Web Text))

Max Activating Token Index: 871

Text #17

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.3262. Min Act: -0.0000

Data Index: 1007600 (C4 (Web Text))

Max Activating Token Index: 433

Text #18

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.2446. Min Act: -0.0000

Data Index: 832089 (C4 (Web Text))

Max Activating Token Index: 346

Text #19

Max Range: 1.8189. Min Range: -1.8189

Max Act: 1.2431. Min Act: -0.0000

Data Index: 124014 (C4 (Web Text))

Max Activating Token Index: 286