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

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

Neuron 3965 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0862. Min Act: -0.0000

Data Index: 925344 (C4 (Web Text))

Max Activating Token Index: 516

Text #1

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0670. Min Act: -0.0000

Data Index: 271233 (C4 (Web Text))

Max Activating Token Index: 985

Text #2

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0302. Min Act: -0.0000

Data Index: 1241853 (C4 (Web Text))

Max Activating Token Index: 146

Text #3

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0042. Min Act: -0.0000

Data Index: 13681 (C4 (Web Text))

Max Activating Token Index: 443

Text #4

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0286. Min Act: -0.0000

Data Index: 454980 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9967. Min Act: -0.0000

Data Index: 905230 (C4 (Web Text))

Max Activating Token Index: 850

Text #6

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9565. Min Act: -0.0000

Data Index: 759740 (C4 (Web Text))

Max Activating Token Index: 173

Text #7

Max Range: 1.0862. Min Range: -1.0862

Max Act: 1.0350. Min Act: -0.0000

Data Index: 543622 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9152. Min Act: -0.0000

Data Index: 699264 (C4 (Web Text))

Max Activating Token Index: 457

Text #9

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9369. Min Act: -0.0000

Data Index: 1197959 (C4 (Web Text))

Max Activating Token Index: 864

Text #10

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9347. Min Act: -0.0000

Data Index: 997939 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9234. Min Act: -0.0000

Data Index: 839150 (C4 (Web Text))

Max Activating Token Index: 730

Text #12

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9250. Min Act: -0.0000

Data Index: 555378 (C4 (Web Text))

Max Activating Token Index: 326

Text #13

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9270. Min Act: -0.0000

Data Index: 1332409 (C4 (Web Text))

Max Activating Token Index: 398

Text #14

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8923. Min Act: -0.0000

Data Index: 1328114 (C4 (Web Text))

Max Activating Token Index: 474

Text #15

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9463. Min Act: -0.0000

Data Index: 468823 (C4 (Web Text))

Max Activating Token Index: 761

Text #16

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8834. Min Act: -0.0000

Data Index: 1020397 (C4 (Web Text))

Max Activating Token Index: 1001

Text #17

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.9390. Min Act: -0.0000

Data Index: 987448 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8489. Min Act: -0.0000

Data Index: 976386 (C4 (Web Text))

Max Activating Token Index: 332

Text #19

Max Range: 1.0862. Min Range: -1.0862

Max Act: 0.8758. Min Act: -0.0000

Data Index: 1125627 (C4 (Web Text))

Max Activating Token Index: 585