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

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

Neuron 3747 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9924. Min Range: -3.9924

Max Act: 3.9924. Min Act: -0.0000

Data Index: 1274433 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 3.9924. Min Range: -3.9924

Max Act: 3.9333. Min Act: -0.0000

Data Index: 256728 (C4 (Web Text))

Max Activating Token Index: 286

Text #2

Max Range: 3.9924. Min Range: -3.9924

Max Act: 3.1958. Min Act: -0.0000

Data Index: 763928 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.9862. Min Act: -0.0000

Data Index: 1362637 (Python Code)

Max Activating Token Index: 200

Text #4

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.7878. Min Act: -0.0000

Data Index: 16231 (C4 (Web Text))

Max Activating Token Index: 557

Text #5

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.5956. Min Act: -0.0000

Data Index: 816502 (C4 (Web Text))

Max Activating Token Index: 640

Text #6

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.3565. Min Act: -0.0000

Data Index: 1610423 (Python Code)

Max Activating Token Index: 670

Text #7

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.0943. Min Act: -0.0000

Data Index: 222926 (C4 (Web Text))

Max Activating Token Index: 264

Text #8

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.2995. Min Act: -0.0000

Data Index: 241112 (C4 (Web Text))

Max Activating Token Index: 938

Text #9

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.1232. Min Act: -0.0000

Data Index: 636469 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.1753. Min Act: -0.0000

Data Index: 1026896 (C4 (Web Text))

Max Activating Token Index: 804

Text #11

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.1494. Min Act: -0.0000

Data Index: 20369 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.3752. Min Act: -0.0000

Data Index: 1288042 (C4 (Web Text))

Max Activating Token Index: 816

Text #13

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.1391. Min Act: -0.0000

Data Index: 271874 (C4 (Web Text))

Max Activating Token Index: 464

Text #14

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.2863. Min Act: -0.0000

Data Index: 52960 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.1857. Min Act: -0.0000

Data Index: 1290108 (C4 (Web Text))

Max Activating Token Index: 507

Text #16

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.3677. Min Act: -0.0000

Data Index: 371771 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.0750. Min Act: -0.0000

Data Index: 819684 (C4 (Web Text))

Max Activating Token Index: 826

Text #18

Max Range: 3.9924. Min Range: -3.9924

Max Act: 1.9557. Min Act: -0.0000

Data Index: 763796 (C4 (Web Text))

Max Activating Token Index: 889

Text #19

Max Range: 3.9924. Min Range: -3.9924

Max Act: 2.1869. Min Act: -0.0000

Data Index: 239509 (C4 (Web Text))

Max Activating Token Index: 934