Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3134 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4820. Min Act: -0.0000

Data Index: 36289 (C4 (Web Text))

Max Activating Token Index: 386

Text #1

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4868. Min Act: -0.0000

Data Index: 949978 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4792. Min Act: -0.0000

Data Index: 519792 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4763. Min Act: -0.0000

Data Index: 932049 (C4 (Web Text))

Max Activating Token Index: 131

Text #4

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4080. Min Act: -0.0001

Data Index: 688572 (C4 (Web Text))

Max Activating Token Index: 930

Text #5

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4023. Min Act: -0.0001

Data Index: 721058 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.4170. Min Act: -0.0000

Data Index: 707709 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3854. Min Act: -0.0001

Data Index: 1224878 (C4 (Web Text))

Max Activating Token Index: 211

Text #8

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3912. Min Act: -0.0000

Data Index: 967236 (C4 (Web Text))

Max Activating Token Index: 323

Text #9

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3885. Min Act: -0.0000

Data Index: 342413 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3740. Min Act: -0.0001

Data Index: 1252559 (C4 (Web Text))

Max Activating Token Index: 830

Text #11

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3647. Min Act: -0.0001

Data Index: 539413 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3751. Min Act: -0.0000

Data Index: 1264899 (C4 (Web Text))

Max Activating Token Index: 948

Text #13

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3705. Min Act: -0.0001

Data Index: 71944 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3682. Min Act: -0.0001

Data Index: 991269 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3546. Min Act: -0.0001

Data Index: 209575 (C4 (Web Text))

Max Activating Token Index: 864

Text #16

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3759. Min Act: -0.0000

Data Index: 996098 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3498. Min Act: -0.0000

Data Index: 117704 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3621. Min Act: -0.0001

Data Index: 758021 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.4868. Min Range: -0.4868

Max Act: 0.3321. Min Act: -0.0001

Data Index: 740263 (C4 (Web Text))

Max Activating Token Index: 942