Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 268 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.3166. Min Act: -0.0000

Data Index: 1139717 (C4 (Web Text))

Max Activating Token Index: 979

Text #1

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2830. Min Act: -0.0001

Data Index: 963411 (C4 (Web Text))

Max Activating Token Index: 651

Text #2

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2686. Min Act: -0.0000

Data Index: 772076 (C4 (Web Text))

Max Activating Token Index: 1000

Text #3

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2586. Min Act: -0.0001

Data Index: 179751 (C4 (Web Text))

Max Activating Token Index: 989

Text #4

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2585. Min Act: -0.0000

Data Index: 269844 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2329. Min Act: -0.0000

Data Index: 842960 (C4 (Web Text))

Max Activating Token Index: 914

Text #6

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2529. Min Act: -0.0000

Data Index: 1324837 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2540. Min Act: -0.0000

Data Index: 903558 (C4 (Web Text))

Max Activating Token Index: 284

Text #8

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2374. Min Act: -0.0000

Data Index: 161408 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2202. Min Act: -0.0001

Data Index: 699138 (C4 (Web Text))

Max Activating Token Index: 889

Text #10

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2392. Min Act: -0.0000

Data Index: 492071 (C4 (Web Text))

Max Activating Token Index: 214

Text #11

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2141. Min Act: -0.0000

Data Index: 1149288 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2355. Min Act: -0.0000

Data Index: 617918 (C4 (Web Text))

Max Activating Token Index: 502

Text #13

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2196. Min Act: -0.0001

Data Index: 355220 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2250. Min Act: -0.0000

Data Index: 961386 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2286. Min Act: -0.0000

Data Index: 8316 (C4 (Web Text))

Max Activating Token Index: 945

Text #16

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2071. Min Act: -0.0000

Data Index: 643185 (C4 (Web Text))

Max Activating Token Index: 308

Text #17

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2280. Min Act: -0.0000

Data Index: 727585 (C4 (Web Text))

Max Activating Token Index: 421

Text #18

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2195. Min Act: -0.0001

Data Index: 34189 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.3166. Min Range: -0.3166

Max Act: 0.2180. Min Act: -0.0000

Data Index: 1015366 (C4 (Web Text))

Max Activating Token Index: 931