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

Dataset: The Pile

Neuron 3909 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1785450 (The Pile)

Max Activating Token Index: 204

Text #1

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4649. Min Act: -0.0000

Data Index: 1884830 (The Pile)

Max Activating Token Index: 254

Text #2

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4678. Min Act: -0.0000

Data Index: 865637 (The Pile)

Max Activating Token Index: 834

Text #3

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4269. Min Act: -0.0000

Data Index: 502404 (The Pile)

Max Activating Token Index: 230

Text #4

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1865549 (The Pile)

Max Activating Token Index: 458

Text #5

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.4202. Min Act: -0.0000

Data Index: 233245 (The Pile)

Max Activating Token Index: 465

Text #6

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3848. Min Act: -0.0000

Data Index: 596811 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3975. Min Act: -0.0000

Data Index: 396607 (The Pile)

Max Activating Token Index: 376

Text #8

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3799. Min Act: -0.0000

Data Index: 252213 (The Pile)

Max Activating Token Index: 528

Text #9

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3933. Min Act: -0.0000

Data Index: 936633 (The Pile)

Max Activating Token Index: 655

Text #10

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1102697 (The Pile)

Max Activating Token Index: 560

Text #11

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3488. Min Act: -0.0000

Data Index: 379741 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1893160 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3470. Min Act: -0.0000

Data Index: 782615 (The Pile)

Max Activating Token Index: 717

Text #14

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3611. Min Act: -0.0000

Data Index: 658782 (The Pile)

Max Activating Token Index: 232

Text #15

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3468. Min Act: -0.0000

Data Index: 1447468 (The Pile)

Max Activating Token Index: 194

Text #16

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3746. Min Act: -0.0000

Data Index: 960765 (The Pile)

Max Activating Token Index: 856

Text #17

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3282. Min Act: -0.0000

Data Index: 1096166 (The Pile)

Max Activating Token Index: 720

Text #18

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3358. Min Act: -0.0000

Data Index: 609816 (The Pile)

Max Activating Token Index: 876

Text #19

Max Range: 0.6186. Min Range: -0.6186

Max Act: 0.3247. Min Act: -0.0000

Data Index: 1570318 (The Pile)

Max Activating Token Index: 376