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

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

Neuron 1324 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: 0.1429. Min Range: -0.1429

Max Act: 0.1429. Min Act: -0.0003

Data Index: 164073 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1290. Min Act: -0.0003

Data Index: 293349 (C4 (Web Text))

Max Activating Token Index: 802

Text #2

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1200. Min Act: -0.0003

Data Index: 707740 (C4 (Web Text))

Max Activating Token Index: 867

Text #3

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1182. Min Act: -0.0003

Data Index: 94766 (C4 (Web Text))

Max Activating Token Index: 383

Text #4

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1225. Min Act: -0.0003

Data Index: 772226 (C4 (Web Text))

Max Activating Token Index: 336

Text #5

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1128. Min Act: -0.0003

Data Index: 1246670 (C4 (Web Text))

Max Activating Token Index: 823

Text #6

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1345. Min Act: -0.0003

Data Index: 1121171 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1211. Min Act: -0.0003

Data Index: 447150 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1158. Min Act: -0.0003

Data Index: 900649 (C4 (Web Text))

Max Activating Token Index: 201

Text #9

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1152. Min Act: -0.0003

Data Index: 445277 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1147. Min Act: -0.0003

Data Index: 123577 (C4 (Web Text))

Max Activating Token Index: 325

Text #11

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1144. Min Act: -0.0003

Data Index: 1352566 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1228. Min Act: -0.0003

Data Index: 511820 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1133. Min Act: -0.0003

Data Index: 1038019 (C4 (Web Text))

Max Activating Token Index: 432

Text #14

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1215. Min Act: -0.0003

Data Index: 869149 (C4 (Web Text))

Max Activating Token Index: 905

Text #15

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1166. Min Act: -0.0003

Data Index: 109311 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1256. Min Act: -0.0003

Data Index: 1254014 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1123. Min Act: -0.0003

Data Index: 24675 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1161. Min Act: -0.0003

Data Index: 1174720 (C4 (Web Text))

Max Activating Token Index: 900

Text #19

Max Range: 0.1429. Min Range: -0.1429

Max Act: 0.1194. Min Act: -0.0003

Data Index: 1266724 (C4 (Web Text))

Max Activating Token Index: 275