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

Dataset: The Pile

Neuron 4621 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.6728. Min Act: -0.0000

Data Index: 50122 (The Pile)

Max Activating Token Index: 937

Text #1

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3609. Min Act: -0.0000

Data Index: 1389461 (The Pile)

Max Activating Token Index: 588

Text #2

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3671. Min Act: -0.0000

Data Index: 886280 (The Pile)

Max Activating Token Index: 201

Text #3

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3561. Min Act: -0.0000

Data Index: 302200 (The Pile)

Max Activating Token Index: 280

Text #4

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1493406 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3278. Min Act: -0.0000

Data Index: 1455525 (The Pile)

Max Activating Token Index: 217

Text #6

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3388. Min Act: -0.0000

Data Index: 1398354 (The Pile)

Max Activating Token Index: 362

Text #7

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3367. Min Act: -0.0000

Data Index: 20555 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3367. Min Act: -0.0000

Data Index: 178144 (The Pile)

Max Activating Token Index: 701

Text #9

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3225. Min Act: -0.0000

Data Index: 425423 (The Pile)

Max Activating Token Index: 823

Text #10

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3378. Min Act: -0.0000

Data Index: 1354158 (The Pile)

Max Activating Token Index: 266

Text #11

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3482. Min Act: -0.0000

Data Index: 1883822 (The Pile)

Max Activating Token Index: 664

Text #12

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3485. Min Act: -0.0000

Data Index: 1102054 (The Pile)

Max Activating Token Index: 793

Text #13

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1989846 (The Pile)

Max Activating Token Index: 1017

Text #14

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3167. Min Act: -0.0000

Data Index: 949179 (The Pile)

Max Activating Token Index: 248

Text #15

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3222. Min Act: -0.0000

Data Index: 1741308 (The Pile)

Max Activating Token Index: 163

Text #16

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3345. Min Act: -0.0000

Data Index: 754625 (The Pile)

Max Activating Token Index: 111

Text #17

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3118. Min Act: -0.0000

Data Index: 142898 (The Pile)

Max Activating Token Index: 625

Text #18

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3328. Min Act: -0.0000

Data Index: 1730006 (The Pile)

Max Activating Token Index: 751

Text #19

Max Range: 0.6728. Min Range: -0.6728

Max Act: 0.3318. Min Act: -0.0000

Data Index: 553511 (The Pile)

Max Activating Token Index: 26