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

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

Neuron 5010 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0503. Min Act: -0.0002

Data Index: 645686 (C4 (Web Text))

Max Activating Token Index: 803

Text #1

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0391. Min Act: -0.0002

Data Index: 1004045 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0310. Min Act: -0.0002

Data Index: 1298565 (C4 (Web Text))

Max Activating Token Index: 323

Text #3

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0312. Min Act: -0.0002

Data Index: 299152 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0313. Min Act: -0.0002

Data Index: 366203 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1187644 (C4 (Web Text))

Max Activating Token Index: 471

Text #6

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1278491 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1103635 (C4 (Web Text))

Max Activating Token Index: 50

Text #8

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0289. Min Act: -0.0002

Data Index: 947311 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0282. Min Act: -0.0002

Data Index: 941203 (C4 (Web Text))

Max Activating Token Index: 246

Text #10

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1016806 (C4 (Web Text))

Max Activating Token Index: 823

Text #11

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0295. Min Act: -0.0002

Data Index: 280052 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0285. Min Act: -0.0002

Data Index: 1340408 (C4 (Web Text))

Max Activating Token Index: 714

Text #13

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1216252 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0276. Min Act: -0.0002

Data Index: 546672 (C4 (Web Text))

Max Activating Token Index: 772

Text #15

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0276. Min Act: -0.0002

Data Index: 707697 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0258. Min Act: -0.0002

Data Index: 880625 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0273. Min Act: -0.0002

Data Index: 280668 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0270. Min Act: -0.0002

Data Index: 312466 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.0503. Min Range: -0.0503

Max Act: 0.0269. Min Act: -0.0002

Data Index: 786509 (C4 (Web Text))

Max Activating Token Index: 195