Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2970 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0003

Data Index: 594165 (C4 (Web Text))

Max Activating Token Index: 393

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0244. Min Act: -0.0003

Data Index: 1144422 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0233. Min Act: -0.0003

Data Index: 557030 (C4 (Web Text))

Max Activating Token Index: 230

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0238. Min Act: -0.0003

Data Index: 612181 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0234. Min Act: -0.0003

Data Index: 469687 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0213. Min Act: -0.0003

Data Index: 262935 (C4 (Web Text))

Max Activating Token Index: 757

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0212. Min Act: -0.0004

Data Index: 835589 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0203. Min Act: -0.0003

Data Index: 246494 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0182. Min Act: -0.0003

Data Index: 1423732 (Python Code)

Max Activating Token Index: 815

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0175. Min Act: -0.0003

Data Index: 643297 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0183. Min Act: -0.0003

Data Index: 807285 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0173. Min Act: -0.0003

Data Index: 205156 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1617141 (Python Code)

Max Activating Token Index: 675

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0172. Min Act: -0.0003

Data Index: 148477 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1468225 (Python Code)

Max Activating Token Index: 316

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1182584 (C4 (Web Text))

Max Activating Token Index: 552

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0162. Min Act: -0.0004

Data Index: 1242082 (C4 (Web Text))

Max Activating Token Index: 503

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1084227 (C4 (Web Text))

Max Activating Token Index: 620

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1274204 (C4 (Web Text))

Max Activating Token Index: 788

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1380692 (Python Code)

Max Activating Token Index: 812