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

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

Neuron 4134 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0428. Min Act: -0.0000

Data Index: 1032765 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0434. Min Act: -0.0001

Data Index: 1030463 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0326. Min Act: -0.0001

Data Index: 732589 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0284. Min Act: -0.0001

Data Index: 436749 (C4 (Web Text))

Max Activating Token Index: 772

Text #4

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0309. Min Act: -0.0001

Data Index: 595384 (C4 (Web Text))

Max Activating Token Index: 245

Text #5

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0295. Min Act: -0.0000

Data Index: 164615 (C4 (Web Text))

Max Activating Token Index: 6

Text #6

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0322. Min Act: -0.0001

Data Index: 663214 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0302. Min Act: -0.0001

Data Index: 209623 (C4 (Web Text))

Max Activating Token Index: 815

Text #8

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0271. Min Act: -0.0000

Data Index: 1264846 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0282. Min Act: -0.0001

Data Index: 630147 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1147083 (C4 (Web Text))

Max Activating Token Index: 147

Text #11

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0248. Min Act: -0.0001

Data Index: 987276 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0235. Min Act: -0.0000

Data Index: 940035 (C4 (Web Text))

Max Activating Token Index: 655

Text #13

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0230. Min Act: -0.0001

Data Index: 1217571 (C4 (Web Text))

Max Activating Token Index: 961

Text #14

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0235. Min Act: -0.0001

Data Index: 836209 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0266. Min Act: -0.0000

Data Index: 761281 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0243. Min Act: -0.0001

Data Index: 11040 (C4 (Web Text))

Max Activating Token Index: 566

Text #17

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0291. Min Act: -0.0001

Data Index: 47812 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0239. Min Act: -0.0000

Data Index: 1014556 (C4 (Web Text))

Max Activating Token Index: 948

Text #19

Max Range: 0.0434. Min Range: -0.0434

Max Act: 0.0237. Min Act: -0.0000

Data Index: 545472 (C4 (Web Text))

Max Activating Token Index: 19