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

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

Neuron 562 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6446. Min Act: -0.0002

Data Index: 1050741 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6575. Min Act: -0.0002

Data Index: 380805 (C4 (Web Text))

Max Activating Token Index: 674

Text #2

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6265. Min Act: -0.0002

Data Index: 643353 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6200. Min Act: -0.0002

Data Index: 751260 (C4 (Web Text))

Max Activating Token Index: 186

Text #4

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5902. Min Act: -0.0002

Data Index: 194944 (C4 (Web Text))

Max Activating Token Index: 472

Text #5

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.6004. Min Act: -0.0002

Data Index: 459707 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5228. Min Act: -0.0002

Data Index: 1030372 (C4 (Web Text))

Max Activating Token Index: 928

Text #7

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5722. Min Act: -0.0001

Data Index: 480323 (C4 (Web Text))

Max Activating Token Index: 911

Text #8

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5785. Min Act: -0.0002

Data Index: 1068314 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5535. Min Act: -0.0001

Data Index: 418479 (C4 (Web Text))

Max Activating Token Index: 266

Text #10

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5577. Min Act: -0.0002

Data Index: 451501 (C4 (Web Text))

Max Activating Token Index: 260

Text #11

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5304. Min Act: -0.0002

Data Index: 354639 (C4 (Web Text))

Max Activating Token Index: 137

Text #12

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5359. Min Act: -0.0002

Data Index: 614869 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5583. Min Act: -0.0002

Data Index: 1289262 (C4 (Web Text))

Max Activating Token Index: 349

Text #14

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5404. Min Act: -0.0002

Data Index: 32576 (C4 (Web Text))

Max Activating Token Index: 81

Text #15

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5540. Min Act: -0.0001

Data Index: 614105 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5468. Min Act: -0.0002

Data Index: 952447 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5089. Min Act: -0.0001

Data Index: 737445 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5275. Min Act: -0.0002

Data Index: 863368 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 0.6575. Min Range: -0.6575

Max Act: 0.5266. Min Act: -0.0002

Data Index: 105447 (C4 (Web Text))

Max Activating Token Index: 576