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

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

Neuron 1979 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3959. Min Act: 0.0001

Data Index: 749295 (C4 (Web Text))

Max Activating Token Index: 906

Text #1

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3811. Min Act: 0.0001

Data Index: 245502 (C4 (Web Text))

Max Activating Token Index: 462

Text #2

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3676. Min Act: -0.0000

Data Index: 760345 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3701. Min Act: -0.0000

Data Index: 1170470 (C4 (Web Text))

Max Activating Token Index: 62

Text #4

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3339. Min Act: -0.0000

Data Index: 867963 (C4 (Web Text))

Max Activating Token Index: 875

Text #5

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3503. Min Act: -0.0000

Data Index: 1295568 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3500. Min Act: -0.0000

Data Index: 1330105 (C4 (Web Text))

Max Activating Token Index: 982

Text #7

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3330. Min Act: -0.0000

Data Index: 1137940 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3312. Min Act: -0.0000

Data Index: 598224 (C4 (Web Text))

Max Activating Token Index: 835

Text #9

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3171. Min Act: -0.0000

Data Index: 823082 (C4 (Web Text))

Max Activating Token Index: 599

Text #10

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3405. Min Act: 0.0001

Data Index: 218835 (C4 (Web Text))

Max Activating Token Index: 74

Text #11

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3198. Min Act: -0.0000

Data Index: 340213 (C4 (Web Text))

Max Activating Token Index: 520

Text #12

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3094. Min Act: -0.0000

Data Index: 575484 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3195. Min Act: -0.0000

Data Index: 396772 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3151. Min Act: -0.0000

Data Index: 27851 (C4 (Web Text))

Max Activating Token Index: 729

Text #15

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3043. Min Act: -0.0000

Data Index: 686224 (C4 (Web Text))

Max Activating Token Index: 46

Text #16

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3111. Min Act: -0.0000

Data Index: 156282 (C4 (Web Text))

Max Activating Token Index: 422

Text #17

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3112. Min Act: -0.0000

Data Index: 554831 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1303837 (C4 (Web Text))

Max Activating Token Index: 661

Text #19

Max Range: 0.3959. Min Range: -0.3959

Max Act: 0.3091. Min Act: -0.0000

Data Index: 1160724 (C4 (Web Text))

Max Activating Token Index: 427