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

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

Neuron 851 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6601. Min Act: -0.0001

Data Index: 855321 (C4 (Web Text))

Max Activating Token Index: 481

Text #1

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6353. Min Act: -0.0001

Data Index: 417695 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6856. Min Act: -0.0001

Data Index: 999011 (C4 (Web Text))

Max Activating Token Index: 582

Text #3

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.6027. Min Act: -0.0001

Data Index: 90848 (C4 (Web Text))

Max Activating Token Index: 524

Text #4

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.5722. Min Act: -0.0001

Data Index: 1057398 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.4721. Min Act: -0.0000

Data Index: 886435 (C4 (Web Text))

Max Activating Token Index: 32

Text #6

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.4357. Min Act: -0.0001

Data Index: 744380 (C4 (Web Text))

Max Activating Token Index: 474

Text #7

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.4352. Min Act: -0.0001

Data Index: 1058557 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3787. Min Act: -0.0001

Data Index: 1063394 (C4 (Web Text))

Max Activating Token Index: 663

Text #9

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.4200. Min Act: -0.0000

Data Index: 1222136 (C4 (Web Text))

Max Activating Token Index: 593

Text #10

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3256. Min Act: -0.0000

Data Index: 1346367 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3527. Min Act: -0.0001

Data Index: 838836 (C4 (Web Text))

Max Activating Token Index: 656

Text #12

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3514. Min Act: -0.0000

Data Index: 170828 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3271. Min Act: -0.0001

Data Index: 652647 (C4 (Web Text))

Max Activating Token Index: 116

Text #14

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3245. Min Act: -0.0001

Data Index: 1175575 (C4 (Web Text))

Max Activating Token Index: 304

Text #15

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3377. Min Act: -0.0000

Data Index: 459452 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3472. Min Act: -0.0001

Data Index: 786104 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3572. Min Act: -0.0001

Data Index: 1159452 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3259. Min Act: -0.0001

Data Index: 480633 (C4 (Web Text))

Max Activating Token Index: 700

Text #19

Max Range: 0.6856. Min Range: -0.6856

Max Act: 0.3242. Min Act: -0.0001

Data Index: 1229959 (C4 (Web Text))

Max Activating Token Index: 663