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

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

Neuron 4388 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1250780 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0293. Min Act: -0.0002

Data Index: 642156 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0276. Min Act: -0.0002

Data Index: 395934 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0267. Min Act: -0.0002

Data Index: 357736 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0263. Min Act: -0.0002

Data Index: 805823 (C4 (Web Text))

Max Activating Token Index: 9

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0260. Min Act: -0.0002

Data Index: 494331 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0259. Min Act: -0.0002

Data Index: 45985 (C4 (Web Text))

Max Activating Token Index: 323

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0249. Min Act: -0.0002

Data Index: 931254 (C4 (Web Text))

Max Activating Token Index: 859

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1054343 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0250. Min Act: -0.0002

Data Index: 973446 (C4 (Web Text))

Max Activating Token Index: 93

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0250. Min Act: -0.0002

Data Index: 471782 (C4 (Web Text))

Max Activating Token Index: 835

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0249. Min Act: -0.0002

Data Index: 302525 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0248. Min Act: -0.0002

Data Index: 700728 (C4 (Web Text))

Max Activating Token Index: 369

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0246. Min Act: -0.0002

Data Index: 521963 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0246. Min Act: -0.0002

Data Index: 762485 (C4 (Web Text))

Max Activating Token Index: 927

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0245. Min Act: -0.0002

Data Index: 3807 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0243. Min Act: -0.0002

Data Index: 1040174 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0243. Min Act: -0.0002

Data Index: 485837 (C4 (Web Text))

Max Activating Token Index: 789

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0243. Min Act: -0.0002

Data Index: 841422 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0239. Min Act: -0.0002

Data Index: 463056 (C4 (Web Text))

Max Activating Token Index: 1019