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

Dataset: The Pile

Neuron 3076 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1391. Min Act: -0.0000

Data Index: 856556 (The Pile)

Max Activating Token Index: 964

Text #1

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1426. Min Act: 0.0000

Data Index: 1851878 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1378. Min Act: -0.0000

Data Index: 200079 (The Pile)

Max Activating Token Index: 560

Text #3

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1398. Min Act: -0.0000

Data Index: 1075395 (The Pile)

Max Activating Token Index: 1002

Text #4

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1270. Min Act: -0.0000

Data Index: 1480721 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1320. Min Act: -0.0000

Data Index: 1027099 (The Pile)

Max Activating Token Index: 829

Text #6

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1249. Min Act: -0.0000

Data Index: 721049 (The Pile)

Max Activating Token Index: 463

Text #7

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1111088 (The Pile)

Max Activating Token Index: 666

Text #8

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1880436 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1152. Min Act: -0.0000

Data Index: 1047191 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1195. Min Act: -0.0000

Data Index: 1324466 (The Pile)

Max Activating Token Index: 586

Text #11

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1134. Min Act: -0.0000

Data Index: 36590 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1380822 (The Pile)

Max Activating Token Index: 1010

Text #13

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1236. Min Act: -0.0000

Data Index: 1188842 (The Pile)

Max Activating Token Index: 718

Text #14

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1110. Min Act: -0.0000

Data Index: 123593 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1313991 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1245. Min Act: -0.0000

Data Index: 1760489 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1122. Min Act: 0.0000

Data Index: 594239 (The Pile)

Max Activating Token Index: 152

Text #18

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1154. Min Act: -0.0000

Data Index: 1943263 (The Pile)

Max Activating Token Index: 949

Text #19

Max Range: 0.1426. Min Range: -0.1426

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1623972 (The Pile)

Max Activating Token Index: 528