Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 336 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0006

Data Index: 462924 (C4 (Web Text))

Max Activating Token Index: 258

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0246. Min Act: -0.0006

Data Index: 461793 (C4 (Web Text))

Max Activating Token Index: 300

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1078786 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0244. Min Act: -0.0006

Data Index: 1192724 (C4 (Web Text))

Max Activating Token Index: 643

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0236. Min Act: -0.0006

Data Index: 290420 (C4 (Web Text))

Max Activating Token Index: 647

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0224. Min Act: -0.0006

Data Index: 669971 (C4 (Web Text))

Max Activating Token Index: 658

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0221. Min Act: -0.0006

Data Index: 124432 (C4 (Web Text))

Max Activating Token Index: 709

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0222. Min Act: -0.0006

Data Index: 167551 (C4 (Web Text))

Max Activating Token Index: 669

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1292180 (C4 (Web Text))

Max Activating Token Index: 831

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0231. Min Act: -0.0006

Data Index: 1270319 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1103573 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0219. Min Act: -0.0006

Data Index: 1036890 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0218. Min Act: -0.0006

Data Index: 705406 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0227. Min Act: -0.0006

Data Index: 863516 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0232. Min Act: -0.0006

Data Index: 305772 (C4 (Web Text))

Max Activating Token Index: 418

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0219. Min Act: -0.0006

Data Index: 231287 (C4 (Web Text))

Max Activating Token Index: 163

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0218. Min Act: -0.0006

Data Index: 635971 (C4 (Web Text))

Max Activating Token Index: 712

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0217. Min Act: -0.0006

Data Index: 1323997 (C4 (Web Text))

Max Activating Token Index: 604

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0211. Min Act: -0.0006

Data Index: 136243 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0212. Min Act: -0.0006

Data Index: 1524110 (Python Code)

Max Activating Token Index: 815