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

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

Neuron 1194 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.9097. Min Act: -0.0000

Data Index: 699662 (C4 (Web Text))

Max Activating Token Index: 434

Text #1

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.7880. Min Act: -0.0000

Data Index: 1132575 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.7175. Min Act: -0.0000

Data Index: 305539 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.6872. Min Act: -0.0000

Data Index: 1130102 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.5111. Min Act: -0.0000

Data Index: 340762 (C4 (Web Text))

Max Activating Token Index: 484

Text #5

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.4039. Min Act: -0.0000

Data Index: 326477 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.3989. Min Act: -0.0000

Data Index: 1324639 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.4045. Min Act: -0.0000

Data Index: 301677 (C4 (Web Text))

Max Activating Token Index: 68

Text #8

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.5508. Min Act: -0.0000

Data Index: 65633 (C4 (Web Text))

Max Activating Token Index: 593

Text #9

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.3091. Min Act: -0.0000

Data Index: 1226659 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.3158. Min Act: -0.0000

Data Index: 279740 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.3948. Min Act: -0.0000

Data Index: 738230 (C4 (Web Text))

Max Activating Token Index: 790

Text #12

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.0941. Min Act: -0.0000

Data Index: 676541 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.1934. Min Act: -0.0000

Data Index: 762509 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.3577. Min Act: -0.0000

Data Index: 285543 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.1135. Min Act: -0.0000

Data Index: 1317241 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.2905. Min Act: -0.0000

Data Index: 1334920 (C4 (Web Text))

Max Activating Token Index: 188

Text #17

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.4813. Min Act: -0.0000

Data Index: 510934 (C4 (Web Text))

Max Activating Token Index: 873

Text #18

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.1266. Min Act: -0.0000

Data Index: 17404 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 3.9097. Min Range: -3.9097

Max Act: 3.1283. Min Act: -0.0000

Data Index: 1084707 (C4 (Web Text))

Max Activating Token Index: 475