Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3493 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 6.8337. Min Range: -6.8337

Max Act: 6.8337. Min Act: -0.0000

Data Index: 1229664 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 6.8337. Min Range: -6.8337

Max Act: 6.0248. Min Act: -0.0000

Data Index: 245569 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 6.8337. Min Range: -6.8337

Max Act: 6.3674. Min Act: -0.0000

Data Index: 293686 (C4 (Web Text))

Max Activating Token Index: 728

Text #3

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.8337. Min Act: -0.0000

Data Index: 713777 (C4 (Web Text))

Max Activating Token Index: 698

Text #4

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.9930. Min Act: -0.0000

Data Index: 970558 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.8265. Min Act: -0.0000

Data Index: 1194862 (C4 (Web Text))

Max Activating Token Index: 160

Text #6

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.7958. Min Act: -0.0000

Data Index: 312957 (C4 (Web Text))

Max Activating Token Index: 886

Text #7

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.7838. Min Act: -0.0000

Data Index: 120561 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.5301. Min Act: -0.0000

Data Index: 539828 (C4 (Web Text))

Max Activating Token Index: 288

Text #9

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.7561. Min Act: -0.0000

Data Index: 810523 (C4 (Web Text))

Max Activating Token Index: 721

Text #10

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.4254. Min Act: -0.0000

Data Index: 111775 (C4 (Web Text))

Max Activating Token Index: 868

Text #11

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.9054. Min Act: -0.0000

Data Index: 8362 (C4 (Web Text))

Max Activating Token Index: 586

Text #12

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.8677. Min Act: -0.0000

Data Index: 196535 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.7613. Min Act: -0.0000

Data Index: 623773 (C4 (Web Text))

Max Activating Token Index: 487

Text #14

Max Range: 6.8337. Min Range: -6.8337

Max Act: 4.9713. Min Act: -0.0000

Data Index: 410602 (C4 (Web Text))

Max Activating Token Index: 803

Text #15

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.4208. Min Act: -0.0000

Data Index: 950924 (C4 (Web Text))

Max Activating Token Index: 476

Text #16

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.3982. Min Act: -0.0000

Data Index: 1010660 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.5362. Min Act: -0.0000

Data Index: 822636 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.3409. Min Act: -0.0000

Data Index: 632404 (C4 (Web Text))

Max Activating Token Index: 234

Text #19

Max Range: 6.8337. Min Range: -6.8337

Max Act: 5.3006. Min Act: -0.0000

Data Index: 1151274 (C4 (Web Text))

Max Activating Token Index: 343