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

Dataset: The Pile

Neuron 335 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.3157. Min Act: -0.0000

Data Index: 547478 (The Pile)

Max Activating Token Index: 815

Text #1

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1292954 (The Pile)

Max Activating Token Index: 1006

Text #2

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1725007 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1454357 (The Pile)

Max Activating Token Index: 179

Text #4

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1081695 (The Pile)

Max Activating Token Index: 790

Text #5

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2404. Min Act: -0.0000

Data Index: 609236 (The Pile)

Max Activating Token Index: 393

Text #6

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2303. Min Act: -0.0000

Data Index: 441577 (The Pile)

Max Activating Token Index: 397

Text #7

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2393. Min Act: -0.0000

Data Index: 1526572 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2384. Min Act: 0.0000

Data Index: 1113667 (The Pile)

Max Activating Token Index: 655

Text #9

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2279. Min Act: -0.0000

Data Index: 107455 (The Pile)

Max Activating Token Index: 660

Text #10

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1093453 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2328. Min Act: -0.0000

Data Index: 255264 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2238. Min Act: -0.0000

Data Index: 191972 (The Pile)

Max Activating Token Index: 127

Text #13

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1519331 (The Pile)

Max Activating Token Index: 579

Text #14

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2212. Min Act: -0.0000

Data Index: 1128035 (The Pile)

Max Activating Token Index: 259

Text #15

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2352. Min Act: -0.0000

Data Index: 973592 (The Pile)

Max Activating Token Index: 98

Text #16

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2184. Min Act: -0.0000

Data Index: 1203575 (The Pile)

Max Activating Token Index: 742

Text #17

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2188. Min Act: 0.0000

Data Index: 749913 (The Pile)

Max Activating Token Index: 136

Text #18

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2188. Min Act: -0.0000

Data Index: 704858 (The Pile)

Max Activating Token Index: 449

Text #19

Max Range: 0.3157. Min Range: -0.3157

Max Act: 0.2155. Min Act: -0.0000

Data Index: 1785038 (The Pile)

Max Activating Token Index: 24