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

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

Neuron 3484 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2819. Min Act: -0.0002

Data Index: 893555 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2550. Min Act: -0.0002

Data Index: 521241 (C4 (Web Text))

Max Activating Token Index: 59

Text #2

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2534. Min Act: -0.0002

Data Index: 779685 (C4 (Web Text))

Max Activating Token Index: 822

Text #3

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2480. Min Act: -0.0002

Data Index: 1160241 (C4 (Web Text))

Max Activating Token Index: 331

Text #4

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2453. Min Act: -0.0002

Data Index: 1653682 (Python Code)

Max Activating Token Index: 2

Text #5

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2453. Min Act: -0.0002

Data Index: 410549 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2376. Min Act: -0.0002

Data Index: 75531 (C4 (Web Text))

Max Activating Token Index: 293

Text #7

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2311. Min Act: -0.0002

Data Index: 80638 (C4 (Web Text))

Max Activating Token Index: 201

Text #8

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2331. Min Act: -0.0002

Data Index: 669332 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2285. Min Act: -0.0002

Data Index: 51833 (C4 (Web Text))

Max Activating Token Index: 187

Text #10

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2275. Min Act: -0.0002

Data Index: 356422 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2277. Min Act: -0.0002

Data Index: 658231 (C4 (Web Text))

Max Activating Token Index: 536

Text #12

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2267. Min Act: -0.0002

Data Index: 20525 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2239. Min Act: -0.0002

Data Index: 274028 (C4 (Web Text))

Max Activating Token Index: 359

Text #14

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2283. Min Act: -0.0002

Data Index: 14341 (C4 (Web Text))

Max Activating Token Index: 519

Text #15

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2190. Min Act: -0.0002

Data Index: 146407 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2230. Min Act: -0.0002

Data Index: 1059289 (C4 (Web Text))

Max Activating Token Index: 732

Text #17

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2213. Min Act: -0.0002

Data Index: 357268 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2193. Min Act: -0.0002

Data Index: 906475 (C4 (Web Text))

Max Activating Token Index: 809

Text #19

Max Range: 0.2819. Min Range: -0.2819

Max Act: 0.2232. Min Act: -0.0002

Data Index: 834645 (C4 (Web Text))

Max Activating Token Index: 952