Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1915 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.3306. Min Act: -0.0000

Data Index: 1226461 (The Pile)

Max Activating Token Index: 684

Text #1

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2817. Min Act: -0.0000

Data Index: 537998 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2730. Min Act: -0.0000

Data Index: 1547806 (The Pile)

Max Activating Token Index: 137

Text #3

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2573. Min Act: -0.0000

Data Index: 275519 (The Pile)

Max Activating Token Index: 656

Text #4

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2499. Min Act: -0.0000

Data Index: 302651 (The Pile)

Max Activating Token Index: 195

Text #5

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1090881 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2252. Min Act: -0.0000

Data Index: 780937 (The Pile)

Max Activating Token Index: 128

Text #7

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2664. Min Act: -0.0000

Data Index: 1134501 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2547. Min Act: -0.0000

Data Index: 730298 (The Pile)

Max Activating Token Index: 128

Text #9

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2550. Min Act: -0.0000

Data Index: 690209 (The Pile)

Max Activating Token Index: 906

Text #10

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2705. Min Act: -0.0000

Data Index: 392530 (The Pile)

Max Activating Token Index: 989

Text #11

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2610. Min Act: -0.0000

Data Index: 1194519 (The Pile)

Max Activating Token Index: 860

Text #12

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2205. Min Act: -0.0000

Data Index: 1938330 (The Pile)

Max Activating Token Index: 674

Text #13

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2274. Min Act: -0.0000

Data Index: 508698 (The Pile)

Max Activating Token Index: 1016

Text #14

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2553. Min Act: -0.0000

Data Index: 1323650 (The Pile)

Max Activating Token Index: 907

Text #15

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2224. Min Act: -0.0000

Data Index: 315164 (The Pile)

Max Activating Token Index: 837

Text #16

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2385. Min Act: -0.0000

Data Index: 844340 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2123. Min Act: -0.0000

Data Index: 37485 (The Pile)

Max Activating Token Index: 729

Text #18

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1950450 (The Pile)

Max Activating Token Index: 896

Text #19

Max Range: 0.3306. Min Range: -0.3306

Max Act: 0.2325. Min Act: -0.0000

Data Index: 1782654 (The Pile)

Max Activating Token Index: 957