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

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

Neuron 5144 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: 0.6872. Min Range: -0.6872

Max Act: 0.6872. Min Act: -0.0002

Data Index: 207530 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6812. Min Act: -0.0002

Data Index: 1317128 (C4 (Web Text))

Max Activating Token Index: 1001

Text #2

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6549. Min Act: -0.0002

Data Index: 90553 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6479. Min Act: -0.0002

Data Index: 724972 (C4 (Web Text))

Max Activating Token Index: 610

Text #4

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6535. Min Act: -0.0002

Data Index: 413869 (C4 (Web Text))

Max Activating Token Index: 386

Text #5

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6493. Min Act: -0.0002

Data Index: 944238 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6471. Min Act: -0.0002

Data Index: 1240741 (C4 (Web Text))

Max Activating Token Index: 825

Text #7

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6512. Min Act: -0.0002

Data Index: 600792 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6311. Min Act: -0.0002

Data Index: 219292 (C4 (Web Text))

Max Activating Token Index: 301

Text #9

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6332. Min Act: -0.0002

Data Index: 688642 (C4 (Web Text))

Max Activating Token Index: 128

Text #10

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6320. Min Act: -0.0002

Data Index: 1260679 (C4 (Web Text))

Max Activating Token Index: 172

Text #11

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6460. Min Act: -0.0002

Data Index: 820209 (C4 (Web Text))

Max Activating Token Index: 203

Text #12

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6428. Min Act: -0.0002

Data Index: 549005 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6350. Min Act: -0.0002

Data Index: 872117 (C4 (Web Text))

Max Activating Token Index: 478

Text #14

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6434. Min Act: -0.0002

Data Index: 742885 (C4 (Web Text))

Max Activating Token Index: 29

Text #15

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6196. Min Act: -0.0002

Data Index: 987351 (C4 (Web Text))

Max Activating Token Index: 177

Text #16

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6221. Min Act: -0.0002

Data Index: 1283839 (C4 (Web Text))

Max Activating Token Index: 193

Text #17

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6206. Min Act: -0.0002

Data Index: 782557 (C4 (Web Text))

Max Activating Token Index: 143

Text #18

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6218. Min Act: -0.0002

Data Index: 1008090 (C4 (Web Text))

Max Activating Token Index: 347

Text #19

Max Range: 0.6872. Min Range: -0.6872

Max Act: 0.6222. Min Act: -0.0002

Data Index: 299332 (C4 (Web Text))

Max Activating Token Index: 46