Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4677 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8429. Min Act: -0.0002

Data Index: 703646 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.9261. Min Act: -0.0002

Data Index: 1004365 (C4 (Web Text))

Max Activating Token Index: 266

Text #2

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8580. Min Act: -0.0002

Data Index: 466421 (C4 (Web Text))

Max Activating Token Index: 31

Text #3

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8234. Min Act: -0.0002

Data Index: 913268 (C4 (Web Text))

Max Activating Token Index: 292

Text #4

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8335. Min Act: -0.0002

Data Index: 269332 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8015. Min Act: -0.0002

Data Index: 844769 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.8009. Min Act: -0.0002

Data Index: 1109440 (C4 (Web Text))

Max Activating Token Index: 456

Text #7

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7743. Min Act: -0.0002

Data Index: 312941 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7711. Min Act: -0.0002

Data Index: 185189 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7926. Min Act: -0.0002

Data Index: 126709 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7334. Min Act: -0.0002

Data Index: 675821 (C4 (Web Text))

Max Activating Token Index: 185

Text #11

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7509. Min Act: -0.0002

Data Index: 79486 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7499. Min Act: -0.0002

Data Index: 304709 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7945. Min Act: -0.0002

Data Index: 562500 (C4 (Web Text))

Max Activating Token Index: 32

Text #14

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7778. Min Act: -0.0002

Data Index: 801871 (C4 (Web Text))

Max Activating Token Index: 347

Text #15

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7196. Min Act: -0.0002

Data Index: 1137170 (C4 (Web Text))

Max Activating Token Index: 36

Text #16

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7439. Min Act: -0.0002

Data Index: 783142 (C4 (Web Text))

Max Activating Token Index: 144

Text #17

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7695. Min Act: -0.0002

Data Index: 1308794 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7378. Min Act: -0.0002

Data Index: 1355847 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 0.9261. Min Range: -0.9261

Max Act: 0.7817. Min Act: -0.0002

Data Index: 12834 (C4 (Web Text))

Max Activating Token Index: 132