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

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

Neuron 4823 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: 0.7833. Min Range: -0.7833

Max Act: 0.7662. Min Act: -0.0002

Data Index: 1315223 (C4 (Web Text))

Max Activating Token Index: 657

Text #1

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.7255. Min Act: -0.0002

Data Index: 40079 (C4 (Web Text))

Max Activating Token Index: 893

Text #2

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.7833. Min Act: -0.0002

Data Index: 116894 (C4 (Web Text))

Max Activating Token Index: 566

Text #3

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6681. Min Act: -0.0002

Data Index: 689805 (C4 (Web Text))

Max Activating Token Index: 787

Text #4

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.7489. Min Act: -0.0002

Data Index: 923964 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.7174. Min Act: -0.0002

Data Index: 797186 (C4 (Web Text))

Max Activating Token Index: 183

Text #6

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.7446. Min Act: -0.0002

Data Index: 1082992 (C4 (Web Text))

Max Activating Token Index: 841

Text #7

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.7213. Min Act: -0.0002

Data Index: 47265 (C4 (Web Text))

Max Activating Token Index: 463

Text #8

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.7565. Min Act: -0.0002

Data Index: 1065640 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6715. Min Act: -0.0002

Data Index: 121687 (C4 (Web Text))

Max Activating Token Index: 338

Text #10

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6250. Min Act: -0.0002

Data Index: 545695 (C4 (Web Text))

Max Activating Token Index: 308

Text #11

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6363. Min Act: -0.0002

Data Index: 550981 (C4 (Web Text))

Max Activating Token Index: 991

Text #12

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6769. Min Act: -0.0002

Data Index: 98929 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6811. Min Act: -0.0002

Data Index: 837565 (C4 (Web Text))

Max Activating Token Index: 627

Text #14

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6093. Min Act: -0.0002

Data Index: 794912 (C4 (Web Text))

Max Activating Token Index: 630

Text #15

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6503. Min Act: -0.0002

Data Index: 1098777 (C4 (Web Text))

Max Activating Token Index: 591

Text #16

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6908. Min Act: -0.0002

Data Index: 1259665 (C4 (Web Text))

Max Activating Token Index: 987

Text #17

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6714. Min Act: -0.0002

Data Index: 141388 (C4 (Web Text))

Max Activating Token Index: 548

Text #18

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6450. Min Act: -0.0002

Data Index: 565127 (C4 (Web Text))

Max Activating Token Index: 672

Text #19

Max Range: 0.7833. Min Range: -0.7833

Max Act: 0.6324. Min Act: -0.0002

Data Index: 258146 (C4 (Web Text))

Max Activating Token Index: 829