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

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

Neuron 3538 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1960. Min Range: -2.1960

Max Act: 2.1960. Min Act: -0.0000

Data Index: 134922 (C4 (Web Text))

Max Activating Token Index: 498

Text #1

Max Range: 2.1960. Min Range: -2.1960

Max Act: 2.1934. Min Act: -0.0000

Data Index: 452822 (C4 (Web Text))

Max Activating Token Index: 366

Text #2

Max Range: 2.1960. Min Range: -2.1960

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1267957 (C4 (Web Text))

Max Activating Token Index: 982

Text #3

Max Range: 2.1960. Min Range: -2.1960

Max Act: 1.1420. Min Act: -0.0000

Data Index: 1038406 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 2.1960. Min Range: -2.1960

Max Act: 1.1150. Min Act: -0.0000

Data Index: 746564 (C4 (Web Text))

Max Activating Token Index: 295

Text #5

Max Range: 2.1960. Min Range: -2.1960

Max Act: 1.0267. Min Act: -0.0000

Data Index: 90417 (C4 (Web Text))

Max Activating Token Index: 612

Text #6

Max Range: 2.1960. Min Range: -2.1960

Max Act: 1.0194. Min Act: -0.0000

Data Index: 135674 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.1960. Min Range: -2.1960

Max Act: 1.0149. Min Act: -0.0000

Data Index: 878310 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 2.1960. Min Range: -2.1960

Max Act: 1.0033. Min Act: -0.0000

Data Index: 638330 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9933. Min Act: -0.0000

Data Index: 280878 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9730. Min Act: -0.0000

Data Index: 315450 (C4 (Web Text))

Max Activating Token Index: 133

Text #11

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9662. Min Act: -0.0000

Data Index: 322046 (C4 (Web Text))

Max Activating Token Index: 984

Text #12

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9577. Min Act: -0.0000

Data Index: 492461 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9385. Min Act: -0.0000

Data Index: 199422 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9414. Min Act: -0.0000

Data Index: 103535 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9344. Min Act: -0.0000

Data Index: 350050 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9605. Min Act: -0.0000

Data Index: 19694 (C4 (Web Text))

Max Activating Token Index: 889

Text #17

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.9081. Min Act: -0.0000

Data Index: 884277 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1299048 (C4 (Web Text))

Max Activating Token Index: 484

Text #19

Max Range: 2.1960. Min Range: -2.1960

Max Act: 0.8666. Min Act: -0.0000

Data Index: 986058 (C4 (Web Text))

Max Activating Token Index: 197