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

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

Neuron 368 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.6733. Min Act: -0.0000

Data Index: 556837 (C4 (Web Text))

Max Activating Token Index: 171

Text #1

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.5703. Min Act: -0.0000

Data Index: 923704 (C4 (Web Text))

Max Activating Token Index: 665

Text #2

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.6491. Min Act: -0.0000

Data Index: 1060704 (C4 (Web Text))

Max Activating Token Index: 38

Text #3

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.3392. Min Act: -0.0000

Data Index: 216266 (C4 (Web Text))

Max Activating Token Index: 216

Text #4

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.3200. Min Act: -0.0000

Data Index: 519911 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.2765. Min Act: -0.0000

Data Index: 141148 (C4 (Web Text))

Max Activating Token Index: 207

Text #6

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.2599. Min Act: -0.0000

Data Index: 446406 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.2497. Min Act: -0.0000

Data Index: 529650 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.2086. Min Act: -0.0000

Data Index: 1037991 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.2815. Min Act: -0.0000

Data Index: 1186680 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1411. Min Act: -0.0000

Data Index: 1053725 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1424. Min Act: -0.0000

Data Index: 1276189 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1190. Min Act: -0.0000

Data Index: 272979 (C4 (Web Text))

Max Activating Token Index: 473

Text #13

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1196. Min Act: -0.0000

Data Index: 583588 (C4 (Web Text))

Max Activating Token Index: 534

Text #14

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1235. Min Act: -0.0000

Data Index: 182367 (C4 (Web Text))

Max Activating Token Index: 13

Text #15

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1284. Min Act: -0.0000

Data Index: 1152013 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1186. Min Act: -0.0000

Data Index: 499512 (C4 (Web Text))

Max Activating Token Index: 314

Text #17

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.1179. Min Act: -0.0000

Data Index: 612059 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.2266. Min Act: -0.0000

Data Index: 1245116 (C4 (Web Text))

Max Activating Token Index: 19

Text #19

Max Range: 2.6733. Min Range: -2.6733

Max Act: 2.2318. Min Act: -0.0000

Data Index: 672138 (C4 (Web Text))

Max Activating Token Index: 17