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

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

Neuron 4615 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.4207. Min Act: -0.0000

Data Index: 1251790 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3731. Min Act: -0.0000

Data Index: 1141714 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3781. Min Act: -0.0000

Data Index: 772609 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3704. Min Act: -0.0000

Data Index: 339677 (C4 (Web Text))

Max Activating Token Index: 363

Text #4

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3413. Min Act: -0.0000

Data Index: 40612 (C4 (Web Text))

Max Activating Token Index: 826

Text #5

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3535. Min Act: -0.0000

Data Index: 118652 (C4 (Web Text))

Max Activating Token Index: 318

Text #6

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3281. Min Act: 0.0001

Data Index: 182617 (C4 (Web Text))

Max Activating Token Index: 402

Text #7

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3264. Min Act: -0.0000

Data Index: 448319 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3320. Min Act: -0.0000

Data Index: 83291 (C4 (Web Text))

Max Activating Token Index: 780

Text #9

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3374. Min Act: -0.0000

Data Index: 1083004 (C4 (Web Text))

Max Activating Token Index: 283

Text #10

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3124. Min Act: -0.0000

Data Index: 515375 (C4 (Web Text))

Max Activating Token Index: 719

Text #11

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1105521 (C4 (Web Text))

Max Activating Token Index: 338

Text #12

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3048. Min Act: -0.0000

Data Index: 813525 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3026. Min Act: -0.0000

Data Index: 1113129 (C4 (Web Text))

Max Activating Token Index: 737

Text #14

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3190. Min Act: -0.0000

Data Index: 1253967 (C4 (Web Text))

Max Activating Token Index: 59

Text #15

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3001. Min Act: -0.0000

Data Index: 545887 (C4 (Web Text))

Max Activating Token Index: 382

Text #16

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3058. Min Act: -0.0000

Data Index: 318264 (C4 (Web Text))

Max Activating Token Index: 589

Text #17

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3160. Min Act: -0.0000

Data Index: 4599 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.2989. Min Act: 0.0000

Data Index: 854855 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 0.4207. Min Range: -0.4207

Max Act: 0.3118. Min Act: -0.0000

Data Index: 354667 (C4 (Web Text))

Max Activating Token Index: 1012