Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1039 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.2685. Min Act: -0.0001

Data Index: 621563 (C4 (Web Text))

Max Activating Token Index: 42

Text #1

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.1831. Min Act: -0.0000

Data Index: 390914 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.2625. Min Act: -0.0000

Data Index: 71482 (C4 (Web Text))

Max Activating Token Index: 804

Text #3

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.2300. Min Act: -0.0000

Data Index: 137457 (C4 (Web Text))

Max Activating Token Index: 72

Text #4

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1310072 (C4 (Web Text))

Max Activating Token Index: 950

Text #5

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.2172. Min Act: -0.0000

Data Index: 1533241 (Python Code)

Max Activating Token Index: 745

Text #6

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.3872. Min Act: -0.0000

Data Index: 979165 (C4 (Web Text))

Max Activating Token Index: 348

Text #7

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.1481. Min Act: -0.0000

Data Index: 889433 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.0629. Min Act: -0.0000

Data Index: 791352 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.2555. Min Act: -0.0000

Data Index: 733493 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.1054. Min Act: -0.0000

Data Index: 1167202 (C4 (Web Text))

Max Activating Token Index: 492

Text #11

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.0226. Min Act: -0.0000

Data Index: 495243 (C4 (Web Text))

Max Activating Token Index: 840

Text #12

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.0106. Min Act: -0.0000

Data Index: 277070 (C4 (Web Text))

Max Activating Token Index: 836

Text #13

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.0941. Min Act: -0.0000

Data Index: 1325453 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 1.3872. Min Range: -1.3872

Max Act: 1.0396. Min Act: -0.0000

Data Index: 585732 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.3872. Min Range: -1.3872

Max Act: 0.9029. Min Act: -0.0000

Data Index: 828745 (C4 (Web Text))

Max Activating Token Index: 866

Text #16

Max Range: 1.3872. Min Range: -1.3872

Max Act: 0.9529. Min Act: -0.0000

Data Index: 649512 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.3872. Min Range: -1.3872

Max Act: 0.9573. Min Act: -0.0000

Data Index: 220833 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 1.3872. Min Range: -1.3872

Max Act: 0.9045. Min Act: -0.0000

Data Index: 883987 (C4 (Web Text))

Max Activating Token Index: 955

Text #19

Max Range: 1.3872. Min Range: -1.3872

Max Act: 0.8680. Min Act: -0.0000

Data Index: 1320723 (C4 (Web Text))

Max Activating Token Index: 945