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

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

Neuron 4540 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: 0.8188. Min Range: -0.8188

Max Act: 0.8188. Min Act: -0.0000

Data Index: 999538 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7720. Min Act: -0.0000

Data Index: 384642 (C4 (Web Text))

Max Activating Token Index: 246

Text #2

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.7428. Min Act: -0.0000

Data Index: 73989 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.4791. Min Act: -0.0000

Data Index: 59535 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6277. Min Act: -0.0000

Data Index: 640414 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1089177 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6463. Min Act: -0.0000

Data Index: 691799 (C4 (Web Text))

Max Activating Token Index: 809

Text #7

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6028. Min Act: -0.0000

Data Index: 682976 (C4 (Web Text))

Max Activating Token Index: 51

Text #8

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.6031. Min Act: -0.0000

Data Index: 283056 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5960. Min Act: -0.0000

Data Index: 1010117 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5582. Min Act: -0.0000

Data Index: 822550 (C4 (Web Text))

Max Activating Token Index: 160

Text #11

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5557. Min Act: -0.0000

Data Index: 1077645 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5867. Min Act: -0.0000

Data Index: 102172 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5512. Min Act: -0.0000

Data Index: 90086 (C4 (Web Text))

Max Activating Token Index: 361

Text #14

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.4966. Min Act: -0.0000

Data Index: 1093552 (C4 (Web Text))

Max Activating Token Index: 790

Text #15

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.4860. Min Act: -0.0000

Data Index: 960458 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5006. Min Act: -0.0000

Data Index: 833210 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.5023. Min Act: -0.0000

Data Index: 784702 (C4 (Web Text))

Max Activating Token Index: 370

Text #18

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.4805. Min Act: -0.0000

Data Index: 895821 (C4 (Web Text))

Max Activating Token Index: 426

Text #19

Max Range: 0.8188. Min Range: -0.8188

Max Act: 0.4701. Min Act: -0.0000

Data Index: 725056 (C4 (Web Text))

Max Activating Token Index: 428