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

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

Neuron 3758 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: 0.0404. Min Range: -0.0404

Max Act: 0.0404. Min Act: -0.0003

Data Index: 531376 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1608130 (Python Code)

Max Activating Token Index: 344

Text #2

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0327. Min Act: -0.0003

Data Index: 1308072 (C4 (Web Text))

Max Activating Token Index: 145

Text #3

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1212410 (C4 (Web Text))

Max Activating Token Index: 882

Text #4

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0331. Min Act: -0.0002

Data Index: 1193448 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0308. Min Act: -0.0002

Data Index: 1551421 (Python Code)

Max Activating Token Index: 337

Text #6

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0315. Min Act: -0.0002

Data Index: 1301340 (C4 (Web Text))

Max Activating Token Index: 334

Text #7

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0304. Min Act: -0.0002

Data Index: 430934 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0310. Min Act: -0.0003

Data Index: 533972 (C4 (Web Text))

Max Activating Token Index: 215

Text #9

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0305. Min Act: -0.0003

Data Index: 809431 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0321. Min Act: -0.0003

Data Index: 277994 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1228596 (C4 (Web Text))

Max Activating Token Index: 636

Text #12

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0291. Min Act: -0.0003

Data Index: 461649 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0297. Min Act: -0.0003

Data Index: 1113509 (C4 (Web Text))

Max Activating Token Index: 439

Text #14

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0293. Min Act: -0.0003

Data Index: 45013 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1078083 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1607751 (Python Code)

Max Activating Token Index: 392

Text #17

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0285. Min Act: -0.0003

Data Index: 569522 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0298. Min Act: -0.0003

Data Index: 378609 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 0.0404. Min Range: -0.0404

Max Act: 0.0289. Min Act: -0.0003

Data Index: 1173466 (C4 (Web Text))

Max Activating Token Index: 279