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

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

Neuron 996 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: 0.0258. Min Range: -0.0258

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1068021 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0249. Min Act: -0.0003

Data Index: 1100714 (C4 (Web Text))

Max Activating Token Index: 103

Text #2

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1608540 (Python Code)

Max Activating Token Index: 246

Text #3

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1574159 (Python Code)

Max Activating Token Index: 243

Text #4

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1445172 (Python Code)

Max Activating Token Index: 633

Text #5

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0203. Min Act: -0.0003

Data Index: 1264949 (C4 (Web Text))

Max Activating Token Index: 557

Text #6

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0212. Min Act: -0.0003

Data Index: 1002760 (C4 (Web Text))

Max Activating Token Index: 383

Text #7

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0203. Min Act: -0.0003

Data Index: 829149 (C4 (Web Text))

Max Activating Token Index: 805

Text #8

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0195. Min Act: -0.0003

Data Index: 1220948 (C4 (Web Text))

Max Activating Token Index: 639

Text #9

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1077897 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0193. Min Act: -0.0003

Data Index: 1083929 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0194. Min Act: -0.0003

Data Index: 971554 (C4 (Web Text))

Max Activating Token Index: 510

Text #12

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0173. Min Act: -0.0003

Data Index: 805067 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0185. Min Act: -0.0003

Data Index: 1378593 (Python Code)

Max Activating Token Index: 169

Text #14

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0181. Min Act: -0.0003

Data Index: 904209 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0184. Min Act: -0.0003

Data Index: 839473 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0184. Min Act: -0.0003

Data Index: 52930 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1435630 (Python Code)

Max Activating Token Index: 574

Text #18

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0187. Min Act: -0.0002

Data Index: 10459 (C4 (Web Text))

Max Activating Token Index: 322

Text #19

Max Range: 0.0258. Min Range: -0.0258

Max Act: 0.0172. Min Act: -0.0003

Data Index: 578867 (C4 (Web Text))

Max Activating Token Index: 267