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

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

Neuron 4942 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: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0003

Data Index: 1166339 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0365. Min Act: -0.0003

Data Index: 578506 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0333. Min Act: -0.0003

Data Index: 1333633 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0317. Min Act: -0.0003

Data Index: 658238 (C4 (Web Text))

Max Activating Token Index: 562

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0302. Min Act: -0.0003

Data Index: 430061 (C4 (Web Text))

Max Activating Token Index: 611

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0291. Min Act: -0.0003

Data Index: 885674 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0276. Min Act: -0.0003

Data Index: 1216594 (C4 (Web Text))

Max Activating Token Index: 176

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0284. Min Act: -0.0003

Data Index: 522662 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0268. Min Act: -0.0003

Data Index: 781054 (C4 (Web Text))

Max Activating Token Index: 381

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1158198 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0252. Min Act: -0.0003

Data Index: 71555 (C4 (Web Text))

Max Activating Token Index: 619

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0239. Min Act: -0.0003

Data Index: 1074841 (C4 (Web Text))

Max Activating Token Index: 428

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1062020 (C4 (Web Text))

Max Activating Token Index: 617

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0246. Min Act: -0.0003

Data Index: 957488 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0241. Min Act: -0.0003

Data Index: 404265 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0251. Min Act: -0.0003

Data Index: 601871 (C4 (Web Text))

Max Activating Token Index: 757

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0241. Min Act: -0.0002

Data Index: 783678 (C4 (Web Text))

Max Activating Token Index: 312

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0235. Min Act: -0.0003

Data Index: 296812 (C4 (Web Text))

Max Activating Token Index: 752

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0236. Min Act: -0.0003

Data Index: 280139 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0239. Min Act: -0.0003

Data Index: 164167 (C4 (Web Text))

Max Activating Token Index: 682