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

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

Neuron 690 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1579504 (Python Code)

Max Activating Token Index: 783

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1491114 (Python Code)

Max Activating Token Index: 224

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0243. Min Act: -0.0003

Data Index: 583495 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1451170 (Python Code)

Max Activating Token Index: 51

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0221. Min Act: -0.0003

Data Index: 1397158 (Python Code)

Max Activating Token Index: 350

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1408215 (Python Code)

Max Activating Token Index: 606

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0222. Min Act: -0.0003

Data Index: 84128 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0227. Min Act: -0.0003

Data Index: 1504903 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1019466 (C4 (Web Text))

Max Activating Token Index: 665

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0212. Min Act: -0.0003

Data Index: 154537 (C4 (Web Text))

Max Activating Token Index: 399

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0199. Min Act: -0.0003

Data Index: 447898 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0200. Min Act: -0.0003

Data Index: 1535432 (Python Code)

Max Activating Token Index: 658

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1367682 (Python Code)

Max Activating Token Index: 182

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0199. Min Act: -0.0003

Data Index: 1499144 (Python Code)

Max Activating Token Index: 108

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1610025 (Python Code)

Max Activating Token Index: 946

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0188. Min Act: -0.0003

Data Index: 693745 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0191. Min Act: -0.0003

Data Index: 540875 (C4 (Web Text))

Max Activating Token Index: 890

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0187. Min Act: -0.0003

Data Index: 294818 (C4 (Web Text))

Max Activating Token Index: 1006

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0190. Min Act: -0.0003

Data Index: 557288 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0186. Min Act: -0.0003

Data Index: 1640372 (Python Code)

Max Activating Token Index: 729