Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1610 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0354. Min Act: -0.0005

Data Index: 224570 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0307. Min Act: -0.0005

Data Index: 1115046 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0300. Min Act: -0.0005

Data Index: 922091 (C4 (Web Text))

Max Activating Token Index: 379

Text #3

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0306. Min Act: -0.0005

Data Index: 1132335 (C4 (Web Text))

Max Activating Token Index: 241

Text #4

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0310. Min Act: -0.0005

Data Index: 833124 (C4 (Web Text))

Max Activating Token Index: 308

Text #5

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1027939 (C4 (Web Text))

Max Activating Token Index: 688

Text #6

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0297. Min Act: -0.0005

Data Index: 505596 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0297. Min Act: -0.0005

Data Index: 861005 (C4 (Web Text))

Max Activating Token Index: 576

Text #8

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0301. Min Act: -0.0005

Data Index: 473422 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0302. Min Act: -0.0005

Data Index: 616302 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0291. Min Act: -0.0005

Data Index: 1120784 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0296. Min Act: -0.0005

Data Index: 1187794 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0290. Min Act: -0.0005

Data Index: 259310 (C4 (Web Text))

Max Activating Token Index: 355

Text #13

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0286. Min Act: -0.0005

Data Index: 231008 (C4 (Web Text))

Max Activating Token Index: 915

Text #14

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0283. Min Act: -0.0005

Data Index: 1106028 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0272. Min Act: -0.0005

Data Index: 1052895 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0274. Min Act: -0.0005

Data Index: 368385 (C4 (Web Text))

Max Activating Token Index: 764

Text #17

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0271. Min Act: -0.0005

Data Index: 427644 (C4 (Web Text))

Max Activating Token Index: 454

Text #18

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0277. Min Act: -0.0005

Data Index: 184650 (C4 (Web Text))

Max Activating Token Index: 43

Text #19

Max Range: 0.0354. Min Range: -0.0354

Max Act: 0.0278. Min Act: -0.0005

Data Index: 1143625 (C4 (Web Text))

Max Activating Token Index: 916