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

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

Neuron 398 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4918. Min Act: -0.0000

Data Index: 1337612 (C4 (Web Text))

Max Activating Token Index: 54

Text #1

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4576. Min Act: -0.0000

Data Index: 889559 (C4 (Web Text))

Max Activating Token Index: 572

Text #2

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3909. Min Act: -0.0000

Data Index: 1328767 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4097. Min Act: -0.0000

Data Index: 739807 (C4 (Web Text))

Max Activating Token Index: 425

Text #4

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1260136 (C4 (Web Text))

Max Activating Token Index: 962

Text #5

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4022. Min Act: -0.0000

Data Index: 339047 (C4 (Web Text))

Max Activating Token Index: 720

Text #6

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.4161. Min Act: -0.0000

Data Index: 779861 (C4 (Web Text))

Max Activating Token Index: 83

Text #7

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3980. Min Act: -0.0000

Data Index: 444667 (C4 (Web Text))

Max Activating Token Index: 977

Text #8

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3776. Min Act: -0.0000

Data Index: 1317837 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1009688 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3668. Min Act: -0.0000

Data Index: 992967 (C4 (Web Text))

Max Activating Token Index: 807

Text #11

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3786. Min Act: -0.0000

Data Index: 785225 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3766. Min Act: -0.0000

Data Index: 1219076 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3726. Min Act: -0.0000

Data Index: 893508 (C4 (Web Text))

Max Activating Token Index: 77

Text #14

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3576. Min Act: -0.0000

Data Index: 772824 (C4 (Web Text))

Max Activating Token Index: 188

Text #15

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3500. Min Act: -0.0000

Data Index: 209268 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3510. Min Act: -0.0000

Data Index: 766018 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3609. Min Act: -0.0000

Data Index: 673975 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3455. Min Act: -0.0000

Data Index: 367709 (C4 (Web Text))

Max Activating Token Index: 743

Text #19

Max Range: 0.4918. Min Range: -0.4918

Max Act: 0.3691. Min Act: -0.0000

Data Index: 599745 (C4 (Web Text))

Max Activating Token Index: 455