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

Dataset: The Pile

Neuron 1652 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: 0.8423. Min Range: -0.8423

Max Act: 0.8365. Min Act: -0.0000

Data Index: 1367632 (The Pile)

Max Activating Token Index: 907

Text #1

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.8423. Min Act: -0.0000

Data Index: 723701 (The Pile)

Max Activating Token Index: 976

Text #2

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7641. Min Act: -0.0000

Data Index: 635091 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.7214. Min Act: -0.0000

Data Index: 971902 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6876. Min Act: -0.0000

Data Index: 577294 (The Pile)

Max Activating Token Index: 204

Text #5

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5872. Min Act: -0.0000

Data Index: 1174356 (The Pile)

Max Activating Token Index: 834

Text #6

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5454. Min Act: -0.0000

Data Index: 1033382 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6382. Min Act: -0.0000

Data Index: 944351 (The Pile)

Max Activating Token Index: 924

Text #8

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.6069. Min Act: -0.0000

Data Index: 668856 (The Pile)

Max Activating Token Index: 107

Text #9

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5545. Min Act: -0.0000

Data Index: 1750892 (The Pile)

Max Activating Token Index: 296

Text #10

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4980. Min Act: -0.0000

Data Index: 1852435 (The Pile)

Max Activating Token Index: 600

Text #11

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5418. Min Act: -0.0000

Data Index: 1575791 (The Pile)

Max Activating Token Index: 144

Text #12

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5360. Min Act: -0.0000

Data Index: 766347 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5369. Min Act: -0.0000

Data Index: 384754 (The Pile)

Max Activating Token Index: 133

Text #14

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4863. Min Act: -0.0000

Data Index: 646986 (The Pile)

Max Activating Token Index: 755

Text #15

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4745. Min Act: -0.0000

Data Index: 1455354 (The Pile)

Max Activating Token Index: 145

Text #16

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1690919 (The Pile)

Max Activating Token Index: 798

Text #17

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.4862. Min Act: -0.0000

Data Index: 1374616 (The Pile)

Max Activating Token Index: 994

Text #18

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5006. Min Act: -0.0000

Data Index: 477647 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.8423. Min Range: -0.8423

Max Act: 0.5476. Min Act: -0.0000

Data Index: 1078950 (The Pile)

Max Activating Token Index: 180