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

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

Neuron 3785 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1364. Min Act: -0.0000

Data Index: 1249450 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1315. Min Act: -0.0000

Data Index: 266573 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1193. Min Act: -0.0000

Data Index: 288962 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1130. Min Act: -0.0000

Data Index: 378970 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1152. Min Act: -0.0000

Data Index: 157959 (C4 (Web Text))

Max Activating Token Index: 977

Text #5

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1111. Min Act: -0.0000

Data Index: 35039 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1166. Min Act: -0.0000

Data Index: 87490 (C4 (Web Text))

Max Activating Token Index: 695

Text #7

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1164. Min Act: -0.0000

Data Index: 1327985 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1032. Min Act: -0.0000

Data Index: 17662 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1147. Min Act: -0.0000

Data Index: 274040 (C4 (Web Text))

Max Activating Token Index: 887

Text #10

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1011. Min Act: -0.0000

Data Index: 284380 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1039. Min Act: -0.0000

Data Index: 92854 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1043. Min Act: -0.0000

Data Index: 984496 (C4 (Web Text))

Max Activating Token Index: 114

Text #13

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1000. Min Act: -0.0000

Data Index: 577636 (C4 (Web Text))

Max Activating Token Index: 609

Text #14

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1024. Min Act: -0.0000

Data Index: 1196785 (C4 (Web Text))

Max Activating Token Index: 424

Text #15

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0983. Min Act: -0.0000

Data Index: 473269 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.0962. Min Act: -0.0000

Data Index: 859404 (C4 (Web Text))

Max Activating Token Index: 827

Text #17

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1049. Min Act: -0.0000

Data Index: 1230697 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1001. Min Act: -0.0000

Data Index: 954541 (C4 (Web Text))

Max Activating Token Index: 459

Text #19

Max Range: 0.1364. Min Range: -0.1364

Max Act: 0.1000. Min Act: -0.0000

Data Index: 398655 (C4 (Web Text))

Max Activating Token Index: 505