Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2290 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.3169. Min Act: -0.0001

Data Index: 271420 (C4 (Web Text))

Max Activating Token Index: 178

Text #1

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2654. Min Act: -0.0001

Data Index: 100872 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2703. Min Act: -0.0001

Data Index: 497436 (C4 (Web Text))

Max Activating Token Index: 270

Text #3

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2311. Min Act: -0.0001

Data Index: 331329 (C4 (Web Text))

Max Activating Token Index: 215

Text #4

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2225. Min Act: -0.0001

Data Index: 1033777 (C4 (Web Text))

Max Activating Token Index: 402

Text #5

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2199. Min Act: -0.0001

Data Index: 983381 (C4 (Web Text))

Max Activating Token Index: 105

Text #6

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2156. Min Act: -0.0001

Data Index: 387414 (C4 (Web Text))

Max Activating Token Index: 296

Text #7

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2097. Min Act: -0.0001

Data Index: 13662 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2315. Min Act: -0.0001

Data Index: 1030964 (C4 (Web Text))

Max Activating Token Index: 295

Text #9

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2275. Min Act: -0.0001

Data Index: 1168387 (C4 (Web Text))

Max Activating Token Index: 149

Text #10

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2201. Min Act: -0.0001

Data Index: 552678 (C4 (Web Text))

Max Activating Token Index: 461

Text #11

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2346. Min Act: -0.0001

Data Index: 845988 (C4 (Web Text))

Max Activating Token Index: 290

Text #12

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2110. Min Act: -0.0001

Data Index: 636741 (C4 (Web Text))

Max Activating Token Index: 484

Text #13

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2177. Min Act: -0.0001

Data Index: 447638 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2102. Min Act: -0.0001

Data Index: 622924 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1891. Min Act: -0.0001

Data Index: 848612 (C4 (Web Text))

Max Activating Token Index: 68

Text #16

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2222. Min Act: -0.0001

Data Index: 629085 (C4 (Web Text))

Max Activating Token Index: 528

Text #17

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.2142. Min Act: -0.0001

Data Index: 1178984 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1346287 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 0.3169. Min Range: -0.3169

Max Act: 0.1983. Min Act: -0.0001

Data Index: 1254181 (C4 (Web Text))

Max Activating Token Index: 323