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

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

Neuron 4952 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0003

Data Index: 852558 (C4 (Web Text))

Max Activating Token Index: 146

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0405. Min Act: -0.0002

Data Index: 545427 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0378. Min Act: -0.0002

Data Index: 64141 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0360. Min Act: -0.0002

Data Index: 240841 (C4 (Web Text))

Max Activating Token Index: 762

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0357. Min Act: -0.0003

Data Index: 736043 (C4 (Web Text))

Max Activating Token Index: 114

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0331. Min Act: -0.0002

Data Index: 531920 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0324. Min Act: -0.0002

Data Index: 493470 (C4 (Web Text))

Max Activating Token Index: 307

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0329. Min Act: -0.0002

Data Index: 551294 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1196801 (C4 (Web Text))

Max Activating Token Index: 494

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0295. Min Act: -0.0002

Data Index: 16128 (C4 (Web Text))

Max Activating Token Index: 777

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0312. Min Act: -0.0002

Data Index: 415639 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0308. Min Act: -0.0002

Data Index: 610743 (C4 (Web Text))

Max Activating Token Index: 930

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0302. Min Act: -0.0002

Data Index: 450332 (C4 (Web Text))

Max Activating Token Index: 367

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0296. Min Act: -0.0002

Data Index: 728454 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0300. Min Act: -0.0002

Data Index: 452002 (C4 (Web Text))

Max Activating Token Index: 457

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0304. Min Act: -0.0003

Data Index: 529980 (C4 (Web Text))

Max Activating Token Index: 204

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0273. Min Act: -0.0002

Data Index: 696353 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0272. Min Act: -0.0003

Data Index: 790887 (C4 (Web Text))

Max Activating Token Index: 264

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0273. Min Act: -0.0003

Data Index: 266491 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0276. Min Act: -0.0002

Data Index: 565678 (C4 (Web Text))

Max Activating Token Index: 243