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

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

Neuron 4834 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: 0.9472. Min Range: -0.9472

Max Act: 0.9360. Min Act: -0.0000

Data Index: 1115537 (C4 (Web Text))

Max Activating Token Index: 407

Text #1

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9472. Min Act: -0.0000

Data Index: 554013 (C4 (Web Text))

Max Activating Token Index: 10

Text #2

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8627. Min Act: -0.0000

Data Index: 543113 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8988. Min Act: -0.0000

Data Index: 394324 (C4 (Web Text))

Max Activating Token Index: 937

Text #4

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8675. Min Act: -0.0000

Data Index: 561684 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8143. Min Act: -0.0000

Data Index: 386168 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8205. Min Act: -0.0000

Data Index: 656113 (C4 (Web Text))

Max Activating Token Index: 140

Text #7

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1139331 (C4 (Web Text))

Max Activating Token Index: 40

Text #8

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8123. Min Act: -0.0000

Data Index: 105721 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7451. Min Act: -0.0000

Data Index: 272069 (C4 (Web Text))

Max Activating Token Index: 425

Text #10

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8135. Min Act: -0.0000

Data Index: 392064 (C4 (Web Text))

Max Activating Token Index: 62

Text #11

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8098. Min Act: -0.0000

Data Index: 443815 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7773. Min Act: -0.0000

Data Index: 895123 (C4 (Web Text))

Max Activating Token Index: 169

Text #13

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8244. Min Act: -0.0000

Data Index: 80460 (C4 (Web Text))

Max Activating Token Index: 677

Text #14

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7511. Min Act: -0.0000

Data Index: 372360 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7541. Min Act: -0.0000

Data Index: 239759 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7597. Min Act: -0.0000

Data Index: 133715 (C4 (Web Text))

Max Activating Token Index: 19

Text #17

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1308282 (C4 (Web Text))

Max Activating Token Index: 312

Text #18

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7718. Min Act: -0.0000

Data Index: 523493 (C4 (Web Text))

Max Activating Token Index: 904

Text #19

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7964. Min Act: -0.0000

Data Index: 524987 (C4 (Web Text))

Max Activating Token Index: 31