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

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

Neuron 1815 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0335. Min Act: -0.0003

Data Index: 1285590 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0320. Min Act: -0.0003

Data Index: 417167 (C4 (Web Text))

Max Activating Token Index: 306

Text #2

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0305. Min Act: -0.0003

Data Index: 1091536 (C4 (Web Text))

Max Activating Token Index: 261

Text #3

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0291. Min Act: -0.0003

Data Index: 616590 (C4 (Web Text))

Max Activating Token Index: 335

Text #4

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1279697 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1134693 (C4 (Web Text))

Max Activating Token Index: 121

Text #6

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1010154 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0280. Min Act: -0.0003

Data Index: 1342120 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0279. Min Act: -0.0003

Data Index: 998544 (C4 (Web Text))

Max Activating Token Index: 347

Text #9

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1145522 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0261. Min Act: -0.0003

Data Index: 1053931 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0276. Min Act: -0.0003

Data Index: 388667 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0269. Min Act: -0.0003

Data Index: 1225669 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0252. Min Act: -0.0003

Data Index: 1164012 (C4 (Web Text))

Max Activating Token Index: 981

Text #14

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0269. Min Act: -0.0003

Data Index: 954034 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0259. Min Act: -0.0003

Data Index: 1212620 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0262. Min Act: -0.0003

Data Index: 309890 (C4 (Web Text))

Max Activating Token Index: 921

Text #17

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0257. Min Act: -0.0003

Data Index: 1290347 (C4 (Web Text))

Max Activating Token Index: 494

Text #18

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0239. Min Act: -0.0003

Data Index: 51741 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.0335. Min Range: -0.0335

Max Act: 0.0245. Min Act: -0.0003

Data Index: 518116 (C4 (Web Text))

Max Activating Token Index: 296