Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4134 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.7370. Min Act: -0.0000

Data Index: 530992 (C4 (Web Text))

Max Activating Token Index: 245

Text #1

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.7096. Min Act: -0.0000

Data Index: 91332 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6257. Min Act: -0.0000

Data Index: 519811 (C4 (Web Text))

Max Activating Token Index: 862

Text #3

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6367. Min Act: -0.0000

Data Index: 1277233 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5763. Min Act: -0.0000

Data Index: 722800 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6105. Min Act: -0.0000

Data Index: 1116855 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.6142. Min Act: -0.0000

Data Index: 836137 (C4 (Web Text))

Max Activating Token Index: 475

Text #7

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5851. Min Act: -0.0000

Data Index: 787473 (C4 (Web Text))

Max Activating Token Index: 628

Text #8

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4679. Min Act: -0.0000

Data Index: 1199474 (C4 (Web Text))

Max Activating Token Index: 825

Text #9

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5158. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 314

Text #10

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5380. Min Act: -0.0000

Data Index: 1157788 (C4 (Web Text))

Max Activating Token Index: 459

Text #11

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5059. Min Act: -0.0000

Data Index: 303498 (C4 (Web Text))

Max Activating Token Index: 550

Text #12

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5138. Min Act: -0.0000

Data Index: 695320 (C4 (Web Text))

Max Activating Token Index: 354

Text #13

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5270. Min Act: -0.0000

Data Index: 1214559 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4789. Min Act: -0.0000

Data Index: 318978 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1356881 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4787. Min Act: -0.0000

Data Index: 887770 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.5057. Min Act: -0.0000

Data Index: 322784 (C4 (Web Text))

Max Activating Token Index: 241

Text #18

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4889. Min Act: -0.0000

Data Index: 983026 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 0.7370. Min Range: -0.7370

Max Act: 0.4836. Min Act: -0.0000

Data Index: 587178 (C4 (Web Text))

Max Activating Token Index: 451