Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 701 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0001

Data Index: 245907 (C4 (Web Text))

Max Activating Token Index: 202

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0300. Min Act: -0.0001

Data Index: 80151 (C4 (Web Text))

Max Activating Token Index: 771

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0307. Min Act: -0.0001

Data Index: 85714 (C4 (Web Text))

Max Activating Token Index: 715

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0301. Min Act: -0.0001

Data Index: 679711 (C4 (Web Text))

Max Activating Token Index: 122

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0290. Min Act: -0.0001

Data Index: 614281 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0290. Min Act: -0.0001

Data Index: 201060 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0263. Min Act: -0.0001

Data Index: 1287703 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0270. Min Act: -0.0001

Data Index: 1249663 (C4 (Web Text))

Max Activating Token Index: 273

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0250. Min Act: -0.0001

Data Index: 1059521 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0267. Min Act: -0.0001

Data Index: 473488 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0235. Min Act: -0.0001

Data Index: 670300 (C4 (Web Text))

Max Activating Token Index: 344

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0241. Min Act: -0.0001

Data Index: 893535 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0245. Min Act: -0.0001

Data Index: 377241 (C4 (Web Text))

Max Activating Token Index: 924

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0260. Min Act: -0.0002

Data Index: 25039 (C4 (Web Text))

Max Activating Token Index: 233

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0226. Min Act: -0.0002

Data Index: 555070 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0243. Min Act: -0.0001

Data Index: 423418 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0239. Min Act: -0.0002

Data Index: 619810 (C4 (Web Text))

Max Activating Token Index: 198

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1058171 (C4 (Web Text))

Max Activating Token Index: 952

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1009540 (C4 (Web Text))

Max Activating Token Index: 726

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0219. Min Act: -0.0001

Data Index: 429557 (C4 (Web Text))

Max Activating Token Index: 310