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

Dataset: The Pile

Neuron 873 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: 0.4297. Min Range: -0.4297

Max Act: 0.4297. Min Act: -0.0000

Data Index: 1066748 (The Pile)

Max Activating Token Index: 724

Text #1

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3522. Min Act: -0.0000

Data Index: 261358 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3259. Min Act: -0.0000

Data Index: 1351031 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3068. Min Act: -0.0000

Data Index: 606281 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3371. Min Act: -0.0000

Data Index: 1117309 (The Pile)

Max Activating Token Index: 665

Text #5

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3040. Min Act: -0.0000

Data Index: 368187 (The Pile)

Max Activating Token Index: 565

Text #6

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3326. Min Act: -0.0000

Data Index: 7242 (The Pile)

Max Activating Token Index: 603

Text #7

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3283. Min Act: -0.0000

Data Index: 691844 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3477. Min Act: -0.0000

Data Index: 1118421 (The Pile)

Max Activating Token Index: 553

Text #9

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3100. Min Act: -0.0000

Data Index: 533172 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3023. Min Act: -0.0000

Data Index: 23525 (The Pile)

Max Activating Token Index: 575

Text #11

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3037. Min Act: -0.0000

Data Index: 885004 (The Pile)

Max Activating Token Index: 746

Text #12

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2923. Min Act: -0.0000

Data Index: 1839742 (The Pile)

Max Activating Token Index: 707

Text #13

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3048. Min Act: -0.0000

Data Index: 1714735 (The Pile)

Max Activating Token Index: 182

Text #14

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2963. Min Act: -0.0000

Data Index: 239803 (The Pile)

Max Activating Token Index: 915

Text #15

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1846810 (The Pile)

Max Activating Token Index: 426

Text #16

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3023. Min Act: -0.0000

Data Index: 400872 (The Pile)

Max Activating Token Index: 313

Text #17

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2948. Min Act: -0.0000

Data Index: 1315650 (The Pile)

Max Activating Token Index: 242

Text #18

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.3157. Min Act: -0.0000

Data Index: 203367 (The Pile)

Max Activating Token Index: 468

Text #19

Max Range: 0.4297. Min Range: -0.4297

Max Act: 0.2740. Min Act: -0.0000

Data Index: 218008 (The Pile)

Max Activating Token Index: 136