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

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

Neuron 818 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: 0.7793. Min Range: -0.7793

Max Act: 0.7793. Min Act: -0.0000

Data Index: 1168840 (C4 (Web Text))

Max Activating Token Index: 266

Text #1

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6480. Min Act: -0.0000

Data Index: 988387 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6204. Min Act: -0.0000

Data Index: 1219594 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1033000 (C4 (Web Text))

Max Activating Token Index: 635

Text #4

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6296. Min Act: -0.0000

Data Index: 775026 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5487. Min Act: -0.0000

Data Index: 991258 (C4 (Web Text))

Max Activating Token Index: 851

Text #6

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6004. Min Act: -0.0000

Data Index: 75455 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.6287. Min Act: -0.0000

Data Index: 31982 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1173760 (C4 (Web Text))

Max Activating Token Index: 451

Text #9

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5757. Min Act: -0.0000

Data Index: 986192 (C4 (Web Text))

Max Activating Token Index: 985

Text #10

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5692. Min Act: -0.0000

Data Index: 977941 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5322. Min Act: -0.0000

Data Index: 173773 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5824. Min Act: -0.0000

Data Index: 617187 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1143753 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5322. Min Act: -0.0000

Data Index: 1555594 (Python Code)

Max Activating Token Index: 209

Text #15

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5326. Min Act: -0.0000

Data Index: 245632 (C4 (Web Text))

Max Activating Token Index: 540

Text #16

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5292. Min Act: -0.0000

Data Index: 440727 (C4 (Web Text))

Max Activating Token Index: 959

Text #17

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.4917. Min Act: -0.0000

Data Index: 1088162 (C4 (Web Text))

Max Activating Token Index: 148

Text #18

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5523. Min Act: -0.0000

Data Index: 798224 (C4 (Web Text))

Max Activating Token Index: 786

Text #19

Max Range: 0.7793. Min Range: -0.7793

Max Act: 0.5331. Min Act: -0.0000

Data Index: 1267116 (C4 (Web Text))

Max Activating Token Index: 588