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

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

Neuron 1431 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.3195. Min Act: -0.0000

Data Index: 1114737 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2965. Min Act: -0.0000

Data Index: 809659 (C4 (Web Text))

Max Activating Token Index: 125

Text #2

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2658. Min Act: -0.0000

Data Index: 255182 (C4 (Web Text))

Max Activating Token Index: 107

Text #3

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2542. Min Act: -0.0000

Data Index: 1270353 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2468. Min Act: -0.0000

Data Index: 1265482 (C4 (Web Text))

Max Activating Token Index: 1020

Text #5

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2469. Min Act: -0.0000

Data Index: 944318 (C4 (Web Text))

Max Activating Token Index: 360

Text #6

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2437. Min Act: -0.0000

Data Index: 618310 (C4 (Web Text))

Max Activating Token Index: 282

Text #7

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1585501 (Python Code)

Max Activating Token Index: 237

Text #8

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2364. Min Act: -0.0000

Data Index: 455718 (C4 (Web Text))

Max Activating Token Index: 734

Text #9

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2294. Min Act: -0.0000

Data Index: 2369 (C4 (Web Text))

Max Activating Token Index: 96

Text #10

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2156. Min Act: -0.0000

Data Index: 791595 (C4 (Web Text))

Max Activating Token Index: 813

Text #11

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2367. Min Act: -0.0000

Data Index: 560455 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1138901 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2136. Min Act: -0.0000

Data Index: 1116065 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2125. Min Act: -0.0000

Data Index: 737594 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2146. Min Act: -0.0000

Data Index: 623797 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2267. Min Act: -0.0000

Data Index: 868440 (C4 (Web Text))

Max Activating Token Index: 96

Text #17

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2204. Min Act: -0.0000

Data Index: 866307 (C4 (Web Text))

Max Activating Token Index: 603

Text #18

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2100. Min Act: -0.0000

Data Index: 86501 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.3195. Min Range: -0.3195

Max Act: 0.2151. Min Act: -0.0000

Data Index: 318713 (C4 (Web Text))

Max Activating Token Index: 472