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

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

Neuron 3352 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0280. Min Range: -1.0280

Max Act: 1.0225. Min Act: -0.0001

Data Index: 1254629 (C4 (Web Text))

Max Activating Token Index: 716

Text #1

Max Range: 1.0280. Min Range: -1.0280

Max Act: 1.0251. Min Act: -0.0001

Data Index: 85252 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 1.0280. Min Range: -1.0280

Max Act: 1.0225. Min Act: -0.0001

Data Index: 50474 (C4 (Web Text))

Max Activating Token Index: 56

Text #3

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9556. Min Act: -0.0001

Data Index: 1160986 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9632. Min Act: -0.0001

Data Index: 451142 (C4 (Web Text))

Max Activating Token Index: 855

Text #5

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9545. Min Act: -0.0001

Data Index: 1030001 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9592. Min Act: -0.0001

Data Index: 210137 (C4 (Web Text))

Max Activating Token Index: 72

Text #7

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9770. Min Act: -0.0001

Data Index: 414702 (C4 (Web Text))

Max Activating Token Index: 946

Text #8

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9595. Min Act: -0.0001

Data Index: 165366 (C4 (Web Text))

Max Activating Token Index: 71

Text #9

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9846. Min Act: -0.0001

Data Index: 152358 (C4 (Web Text))

Max Activating Token Index: 410

Text #10

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9558. Min Act: -0.0001

Data Index: 1317401 (C4 (Web Text))

Max Activating Token Index: 28

Text #11

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9546. Min Act: -0.0001

Data Index: 568300 (C4 (Web Text))

Max Activating Token Index: 33

Text #12

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9277. Min Act: -0.0001

Data Index: 1264269 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9459. Min Act: -0.0001

Data Index: 1034416 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9504. Min Act: -0.0001

Data Index: 851169 (C4 (Web Text))

Max Activating Token Index: 866

Text #15

Max Range: 1.0280. Min Range: -1.0280

Max Act: 1.0019. Min Act: -0.0001

Data Index: 1094794 (C4 (Web Text))

Max Activating Token Index: 707

Text #16

Max Range: 1.0280. Min Range: -1.0280

Max Act: 1.0280. Min Act: -0.0001

Data Index: 849707 (C4 (Web Text))

Max Activating Token Index: 1008

Text #17

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9061. Min Act: -0.0001

Data Index: 834947 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9037. Min Act: -0.0001

Data Index: 866101 (C4 (Web Text))

Max Activating Token Index: 8

Text #19

Max Range: 1.0280. Min Range: -1.0280

Max Act: 0.9274. Min Act: -0.0001

Data Index: 916683 (C4 (Web Text))

Max Activating Token Index: 57