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

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

Neuron 980 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0003

Data Index: 738974 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0392. Min Act: -0.0003

Data Index: 78558 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0366. Min Act: -0.0003

Data Index: 1118321 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0351. Min Act: -0.0003

Data Index: 509127 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1166839 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1316517 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0347. Min Act: -0.0002

Data Index: 89823 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0331. Min Act: -0.0002

Data Index: 380569 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0327. Min Act: -0.0003

Data Index: 80040 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0321. Min Act: -0.0003

Data Index: 445488 (C4 (Web Text))

Max Activating Token Index: 873

Text #10

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0317. Min Act: -0.0003

Data Index: 69188 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0316. Min Act: -0.0003

Data Index: 169328 (C4 (Web Text))

Max Activating Token Index: 270

Text #12

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0315. Min Act: -0.0003

Data Index: 394803 (C4 (Web Text))

Max Activating Token Index: 672

Text #13

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0306. Min Act: -0.0002

Data Index: 277746 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0311. Min Act: -0.0003

Data Index: 436242 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0311. Min Act: -0.0003

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0308. Min Act: -0.0002

Data Index: 540135 (C4 (Web Text))

Max Activating Token Index: 380

Text #17

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0300. Min Act: -0.0003

Data Index: 1355890 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0305. Min Act: -0.0003

Data Index: 838431 (C4 (Web Text))

Max Activating Token Index: 93

Text #19

Max Range: 0.0392. Min Range: -0.0392

Max Act: 0.0302. Min Act: -0.0003

Data Index: 825367 (C4 (Web Text))

Max Activating Token Index: 303