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

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

Neuron 361 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0606. Min Range: -1.0606

Max Act: 1.0606. Min Act: -0.0001

Data Index: 426398 (C4 (Web Text))

Max Activating Token Index: 336

Text #1

Max Range: 1.0606. Min Range: -1.0606

Max Act: 1.0205. Min Act: -0.0001

Data Index: 72697 (C4 (Web Text))

Max Activating Token Index: 53

Text #2

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9739. Min Act: -0.0001

Data Index: 825377 (C4 (Web Text))

Max Activating Token Index: 438

Text #3

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9704. Min Act: -0.0001

Data Index: 808789 (C4 (Web Text))

Max Activating Token Index: 291

Text #4

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.8722. Min Act: -0.0001

Data Index: 954315 (C4 (Web Text))

Max Activating Token Index: 812

Text #5

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9509. Min Act: -0.0001

Data Index: 600768 (C4 (Web Text))

Max Activating Token Index: 368

Text #6

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9720. Min Act: -0.0002

Data Index: 680622 (C4 (Web Text))

Max Activating Token Index: 329

Text #7

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9128. Min Act: -0.0001

Data Index: 404968 (C4 (Web Text))

Max Activating Token Index: 514

Text #8

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9141. Min Act: -0.0002

Data Index: 1091418 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9072. Min Act: -0.0001

Data Index: 978070 (C4 (Web Text))

Max Activating Token Index: 895

Text #10

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9016. Min Act: -0.0001

Data Index: 91779 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9177. Min Act: -0.0001

Data Index: 323942 (C4 (Web Text))

Max Activating Token Index: 450

Text #12

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.8830. Min Act: -0.0002

Data Index: 198800 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9538. Min Act: -0.0001

Data Index: 1133377 (C4 (Web Text))

Max Activating Token Index: 514

Text #14

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9207. Min Act: -0.0001

Data Index: 291980 (C4 (Web Text))

Max Activating Token Index: 834

Text #15

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.8647. Min Act: -0.0002

Data Index: 112264 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.8841. Min Act: -0.0001

Data Index: 347419 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.9113. Min Act: -0.0001

Data Index: 1160280 (C4 (Web Text))

Max Activating Token Index: 57

Text #18

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.8557. Min Act: -0.0001

Data Index: 708950 (C4 (Web Text))

Max Activating Token Index: 1000

Text #19

Max Range: 1.0606. Min Range: -1.0606

Max Act: 0.8485. Min Act: -0.0001

Data Index: 155456 (C4 (Web Text))

Max Activating Token Index: 918