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

Dataset: The Pile

Neuron 71 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: 0.2390. Min Range: -0.2390

Max Act: 0.2390. Min Act: -0.0000

Data Index: 85905 (The Pile)

Max Activating Token Index: 674

Text #1

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2385. Min Act: -0.0000

Data Index: 1403347 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2339. Min Act: -0.0000

Data Index: 1426928 (The Pile)

Max Activating Token Index: 655

Text #3

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2348. Min Act: -0.0000

Data Index: 505770 (The Pile)

Max Activating Token Index: 496

Text #4

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2177. Min Act: -0.0000

Data Index: 1444473 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2165. Min Act: -0.0000

Data Index: 1148297 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2038. Min Act: -0.0000

Data Index: 1956833 (The Pile)

Max Activating Token Index: 1019

Text #7

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1548442 (The Pile)

Max Activating Token Index: 562

Text #8

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1231402 (The Pile)

Max Activating Token Index: 471

Text #9

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2127. Min Act: -0.0000

Data Index: 728800 (The Pile)

Max Activating Token Index: 573

Text #10

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2208. Min Act: -0.0000

Data Index: 845576 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2048. Min Act: -0.0000

Data Index: 669025 (The Pile)

Max Activating Token Index: 153

Text #12

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2100. Min Act: -0.0000

Data Index: 1681138 (The Pile)

Max Activating Token Index: 483

Text #13

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2077. Min Act: -0.0000

Data Index: 1529094 (The Pile)

Max Activating Token Index: 456

Text #14

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2058. Min Act: -0.0000

Data Index: 1692946 (The Pile)

Max Activating Token Index: 990

Text #15

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1919. Min Act: -0.0000

Data Index: 1420738 (The Pile)

Max Activating Token Index: 630

Text #16

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1959. Min Act: -0.0000

Data Index: 767073 (The Pile)

Max Activating Token Index: 333

Text #17

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1966. Min Act: -0.0000

Data Index: 487747 (The Pile)

Max Activating Token Index: 52

Text #18

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.1961. Min Act: -0.0000

Data Index: 747762 (The Pile)

Max Activating Token Index: 165

Text #19

Max Range: 0.2390. Min Range: -0.2390

Max Act: 0.2070. Min Act: -0.0000

Data Index: 880482 (The Pile)

Max Activating Token Index: 60