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

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

Neuron 3279 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0294. Min Act: -0.0000

Data Index: 674826 (C4 (Web Text))

Max Activating Token Index: 110

Text #1

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0261. Min Act: -0.0000

Data Index: 679238 (C4 (Web Text))

Max Activating Token Index: 350

Text #2

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0218. Min Act: -0.0000

Data Index: 113877 (C4 (Web Text))

Max Activating Token Index: 941

Text #3

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0250. Min Act: -0.0000

Data Index: 195364 (C4 (Web Text))

Max Activating Token Index: 552

Text #4

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0217. Min Act: -0.0000

Data Index: 437838 (C4 (Web Text))

Max Activating Token Index: 142

Text #5

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0221. Min Act: -0.0000

Data Index: 740200 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0218. Min Act: -0.0000

Data Index: 296327 (C4 (Web Text))

Max Activating Token Index: 747

Text #7

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0214. Min Act: -0.0000

Data Index: 479525 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0222. Min Act: -0.0000

Data Index: 1426378 (Python Code)

Max Activating Token Index: 721

Text #9

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0192. Min Act: -0.0000

Data Index: 546656 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0223. Min Act: -0.0000

Data Index: 1513299 (Python Code)

Max Activating Token Index: 242

Text #11

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0181. Min Act: -0.0000

Data Index: 911903 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0203. Min Act: -0.0000

Data Index: 145293 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0198. Min Act: -0.0000

Data Index: 799876 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0175. Min Act: -0.0000

Data Index: 283421 (C4 (Web Text))

Max Activating Token Index: 505

Text #15

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1131326 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0193. Min Act: -0.0000

Data Index: 1637895 (Python Code)

Max Activating Token Index: 565

Text #17

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0182. Min Act: -0.0000

Data Index: 588847 (C4 (Web Text))

Max Activating Token Index: 909

Text #18

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0177. Min Act: -0.0000

Data Index: 1084755 (C4 (Web Text))

Max Activating Token Index: 87

Text #19

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0176. Min Act: -0.0000

Data Index: 936473 (C4 (Web Text))

Max Activating Token Index: 873