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

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

Neuron 4268 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0378. Min Act: -0.0003

Data Index: 1129099 (C4 (Web Text))

Max Activating Token Index: 762

Text #1

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0364. Min Act: -0.0003

Data Index: 199177 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0344. Min Act: -0.0003

Data Index: 1021114 (C4 (Web Text))

Max Activating Token Index: 79

Text #3

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0340. Min Act: -0.0003

Data Index: 418542 (C4 (Web Text))

Max Activating Token Index: 500

Text #4

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0339. Min Act: -0.0003

Data Index: 237936 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0345. Min Act: -0.0003

Data Index: 1214371 (C4 (Web Text))

Max Activating Token Index: 274

Text #6

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0315. Min Act: -0.0003

Data Index: 434535 (C4 (Web Text))

Max Activating Token Index: 298

Text #7

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0339. Min Act: -0.0003

Data Index: 1108860 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0322. Min Act: -0.0003

Data Index: 966487 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0343. Min Act: -0.0003

Data Index: 964103 (C4 (Web Text))

Max Activating Token Index: 119

Text #10

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0321. Min Act: -0.0003

Data Index: 948691 (C4 (Web Text))

Max Activating Token Index: 246

Text #11

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0327. Min Act: -0.0003

Data Index: 39780 (C4 (Web Text))

Max Activating Token Index: 679

Text #12

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0328. Min Act: -0.0003

Data Index: 12466 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0314. Min Act: -0.0003

Data Index: 745737 (C4 (Web Text))

Max Activating Token Index: 226

Text #14

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1003728 (C4 (Web Text))

Max Activating Token Index: 591

Text #15

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0320. Min Act: -0.0003

Data Index: 828083 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0316. Min Act: -0.0003

Data Index: 156780 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0313. Min Act: -0.0003

Data Index: 1071884 (C4 (Web Text))

Max Activating Token Index: 438

Text #18

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0320. Min Act: -0.0003

Data Index: 735211 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0378. Min Range: -0.0378

Max Act: 0.0317. Min Act: -0.0003

Data Index: 565322 (C4 (Web Text))

Max Activating Token Index: 509