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

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

Neuron 98 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: 0.0327. Min Range: -0.0327

Max Act: 0.0327. Min Act: -0.0002

Data Index: 570761 (C4 (Web Text))

Max Activating Token Index: 118

Text #1

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1242285 (C4 (Web Text))

Max Activating Token Index: 388

Text #2

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1269366 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0280. Min Act: -0.0002

Data Index: 98752 (C4 (Web Text))

Max Activating Token Index: 653

Text #4

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0277. Min Act: -0.0002

Data Index: 148081 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0290. Min Act: -0.0002

Data Index: 641554 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0250. Min Act: -0.0002

Data Index: 232526 (C4 (Web Text))

Max Activating Token Index: 524

Text #7

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1192824 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0247. Min Act: -0.0002

Data Index: 329058 (C4 (Web Text))

Max Activating Token Index: 197

Text #9

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0234. Min Act: -0.0002

Data Index: 118665 (C4 (Web Text))

Max Activating Token Index: 647

Text #10

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0251. Min Act: -0.0002

Data Index: 561454 (C4 (Web Text))

Max Activating Token Index: 841

Text #11

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0237. Min Act: -0.0002

Data Index: 463046 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0240. Min Act: -0.0002

Data Index: 207306 (C4 (Web Text))

Max Activating Token Index: 179

Text #13

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0232. Min Act: -0.0002

Data Index: 969608 (C4 (Web Text))

Max Activating Token Index: 165

Text #14

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0230. Min Act: -0.0002

Data Index: 294682 (C4 (Web Text))

Max Activating Token Index: 71

Text #15

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0219. Min Act: -0.0002

Data Index: 837612 (C4 (Web Text))

Max Activating Token Index: 816

Text #16

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1457347 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0231. Min Act: -0.0002

Data Index: 185701 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0233. Min Act: -0.0002

Data Index: 545926 (C4 (Web Text))

Max Activating Token Index: 80

Text #19

Max Range: 0.0327. Min Range: -0.0327

Max Act: 0.0244. Min Act: -0.0002

Data Index: 726770 (C4 (Web Text))

Max Activating Token Index: 368