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

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

Neuron 4097 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: 0.3066. Min Range: -0.3066

Max Act: 0.3066. Min Act: -0.0000

Data Index: 876773 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2916. Min Act: -0.0000

Data Index: 795908 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2953. Min Act: -0.0000

Data Index: 640775 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2814. Min Act: -0.0000

Data Index: 1047540 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2856. Min Act: -0.0000

Data Index: 793313 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2833. Min Act: -0.0000

Data Index: 1144677 (C4 (Web Text))

Max Activating Token Index: 862

Text #6

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2913. Min Act: -0.0000

Data Index: 476830 (C4 (Web Text))

Max Activating Token Index: 881

Text #7

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2711. Min Act: 0.0000

Data Index: 1030637 (C4 (Web Text))

Max Activating Token Index: 973

Text #8

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2679. Min Act: -0.0000

Data Index: 575711 (C4 (Web Text))

Max Activating Token Index: 355

Text #9

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2549. Min Act: -0.0000

Data Index: 588298 (C4 (Web Text))

Max Activating Token Index: 831

Text #10

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2464. Min Act: 0.0001

Data Index: 1035671 (C4 (Web Text))

Max Activating Token Index: 548

Text #11

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2549. Min Act: -0.0000

Data Index: 1340164 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2538. Min Act: -0.0000

Data Index: 440044 (C4 (Web Text))

Max Activating Token Index: 590

Text #13

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2463. Min Act: -0.0000

Data Index: 891591 (C4 (Web Text))

Max Activating Token Index: 501

Text #14

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2438. Min Act: 0.0000

Data Index: 787318 (C4 (Web Text))

Max Activating Token Index: 926

Text #15

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2420. Min Act: -0.0000

Data Index: 816481 (C4 (Web Text))

Max Activating Token Index: 372

Text #16

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2412. Min Act: -0.0000

Data Index: 349735 (C4 (Web Text))

Max Activating Token Index: 817

Text #17

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2468. Min Act: -0.0000

Data Index: 263287 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2281. Min Act: -0.0000

Data Index: 1122258 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.3066. Min Range: -0.3066

Max Act: 0.2350. Min Act: -0.0000

Data Index: 825296 (C4 (Web Text))

Max Activating Token Index: 975