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

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

Neuron 5046 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1574524 (Python Code)

Max Activating Token Index: 5

Text #1

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0297. Min Act: -0.0002

Data Index: 1323457 (C4 (Web Text))

Max Activating Token Index: 88

Text #2

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0231. Min Act: -0.0002

Data Index: 493194 (C4 (Web Text))

Max Activating Token Index: 596

Text #3

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0229. Min Act: -0.0002

Data Index: 610298 (C4 (Web Text))

Max Activating Token Index: 877

Text #4

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1236991 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0201. Min Act: -0.0002

Data Index: 329932 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0226. Min Act: -0.0002

Data Index: 1125366 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0268. Min Act: -0.0002

Data Index: 447915 (C4 (Web Text))

Max Activating Token Index: 219

Text #8

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1551946 (Python Code)

Max Activating Token Index: 806

Text #9

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0210. Min Act: -0.0002

Data Index: 1624228 (Python Code)

Max Activating Token Index: 204

Text #10

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0203. Min Act: -0.0002

Data Index: 452002 (C4 (Web Text))

Max Activating Token Index: 476

Text #11

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0177. Min Act: -0.0002

Data Index: 890674 (C4 (Web Text))

Max Activating Token Index: 781

Text #12

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1522154 (Python Code)

Max Activating Token Index: 862

Text #13

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0203. Min Act: -0.0002

Data Index: 985937 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0197. Min Act: -0.0002

Data Index: 1502482 (Python Code)

Max Activating Token Index: 6

Text #15

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0196. Min Act: -0.0002

Data Index: 757163 (C4 (Web Text))

Max Activating Token Index: 931

Text #16

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0193. Min Act: -0.0002

Data Index: 1450058 (Python Code)

Max Activating Token Index: 47

Text #17

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0185. Min Act: -0.0002

Data Index: 1370267 (Python Code)

Max Activating Token Index: 1004

Text #18

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0212. Min Act: -0.0002

Data Index: 1297108 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.0297. Min Range: -0.0297

Max Act: 0.0177. Min Act: -0.0002

Data Index: 1371401 (Python Code)

Max Activating Token Index: 999