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

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

Neuron 4066 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: 0.2649. Min Range: -0.2649

Max Act: 0.2649. Min Act: -0.0002

Data Index: 262190 (C4 (Web Text))

Max Activating Token Index: 852

Text #1

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2568. Min Act: -0.0002

Data Index: 693687 (C4 (Web Text))

Max Activating Token Index: 273

Text #2

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2422. Min Act: -0.0002

Data Index: 523505 (C4 (Web Text))

Max Activating Token Index: 649

Text #3

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2365. Min Act: -0.0002

Data Index: 594913 (C4 (Web Text))

Max Activating Token Index: 598

Text #4

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1954. Min Act: -0.0002

Data Index: 613414 (C4 (Web Text))

Max Activating Token Index: 954

Text #5

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2117. Min Act: -0.0002

Data Index: 956414 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2226. Min Act: -0.0002

Data Index: 1063657 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2137. Min Act: -0.0002

Data Index: 906249 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1974. Min Act: -0.0002

Data Index: 452897 (C4 (Web Text))

Max Activating Token Index: 995

Text #9

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2115. Min Act: -0.0002

Data Index: 167923 (C4 (Web Text))

Max Activating Token Index: 325

Text #10

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2108. Min Act: -0.0002

Data Index: 1210105 (C4 (Web Text))

Max Activating Token Index: 560

Text #11

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2196. Min Act: -0.0002

Data Index: 896123 (C4 (Web Text))

Max Activating Token Index: 166

Text #12

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1981. Min Act: -0.0002

Data Index: 1160782 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2177. Min Act: -0.0002

Data Index: 600729 (C4 (Web Text))

Max Activating Token Index: 360

Text #14

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2019. Min Act: -0.0002

Data Index: 299241 (C4 (Web Text))

Max Activating Token Index: 672

Text #15

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1947. Min Act: -0.0002

Data Index: 1082131 (C4 (Web Text))

Max Activating Token Index: 43

Text #16

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2088. Min Act: -0.0002

Data Index: 580392 (C4 (Web Text))

Max Activating Token Index: 402

Text #17

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1940. Min Act: -0.0002

Data Index: 924529 (C4 (Web Text))

Max Activating Token Index: 485

Text #18

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.2140. Min Act: -0.0002

Data Index: 283213 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 0.2649. Min Range: -0.2649

Max Act: 0.1844. Min Act: -0.0002

Data Index: 909312 (C4 (Web Text))

Max Activating Token Index: 562