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

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

Neuron 3605 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0002

Data Index: 498785 (C4 (Web Text))

Max Activating Token Index: 272

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0336. Min Act: -0.0002

Data Index: 105707 (C4 (Web Text))

Max Activating Token Index: 871

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0329. Min Act: -0.0002

Data Index: 1323644 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0320. Min Act: -0.0002

Data Index: 1205441 (C4 (Web Text))

Max Activating Token Index: 690

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0322. Min Act: -0.0002

Data Index: 229568 (C4 (Web Text))

Max Activating Token Index: 237

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1188759 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0315. Min Act: -0.0002

Data Index: 681003 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0306. Min Act: -0.0002

Data Index: 1245144 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0294. Min Act: -0.0002

Data Index: 689410 (C4 (Web Text))

Max Activating Token Index: 669

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1110482 (C4 (Web Text))

Max Activating Token Index: 175

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0306. Min Act: -0.0002

Data Index: 831496 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0299. Min Act: -0.0002

Data Index: 675945 (C4 (Web Text))

Max Activating Token Index: 900

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0303. Min Act: -0.0002

Data Index: 666900 (C4 (Web Text))

Max Activating Token Index: 469

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0287. Min Act: -0.0002

Data Index: 201953 (C4 (Web Text))

Max Activating Token Index: 649

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0308. Min Act: -0.0002

Data Index: 454638 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1028098 (C4 (Web Text))

Max Activating Token Index: 117

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0303. Min Act: -0.0002

Data Index: 737999 (C4 (Web Text))

Max Activating Token Index: 185

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1077341 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0284. Min Act: -0.0002

Data Index: 100231 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0295. Min Act: -0.0002

Data Index: 248890 (C4 (Web Text))

Max Activating Token Index: 241