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

Dataset: The Pile

Neuron 2152 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: 0.2803. Min Range: -0.2803

Max Act: 0.2803. Min Act: -0.0000

Data Index: 843224 (The Pile)

Max Activating Token Index: 542

Text #1

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2446. Min Act: -0.0000

Data Index: 656958 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1687711 (The Pile)

Max Activating Token Index: 759

Text #3

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2452. Min Act: -0.0000

Data Index: 889181 (The Pile)

Max Activating Token Index: 519

Text #4

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2403. Min Act: -0.0000

Data Index: 1795230 (The Pile)

Max Activating Token Index: 265

Text #5

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2518. Min Act: -0.0000

Data Index: 1895792 (The Pile)

Max Activating Token Index: 918

Text #6

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2447. Min Act: -0.0000

Data Index: 891975 (The Pile)

Max Activating Token Index: 496

Text #7

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2274. Min Act: -0.0000

Data Index: 766431 (The Pile)

Max Activating Token Index: 279

Text #8

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2341. Min Act: -0.0000

Data Index: 755401 (The Pile)

Max Activating Token Index: 744

Text #9

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2258. Min Act: -0.0000

Data Index: 1746776 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2148. Min Act: -0.0000

Data Index: 1924011 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2050. Min Act: -0.0000

Data Index: 1006315 (The Pile)

Max Activating Token Index: 798

Text #12

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2166. Min Act: -0.0000

Data Index: 1607946 (The Pile)

Max Activating Token Index: 95

Text #13

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2344. Min Act: -0.0000

Data Index: 725653 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2148. Min Act: -0.0000

Data Index: 406701 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2055. Min Act: -0.0000

Data Index: 1262216 (The Pile)

Max Activating Token Index: 688

Text #16

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2108. Min Act: 0.0000

Data Index: 1916204 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2115. Min Act: -0.0000

Data Index: 835531 (The Pile)

Max Activating Token Index: 77

Text #18

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.1992. Min Act: -0.0000

Data Index: 1824554 (The Pile)

Max Activating Token Index: 203

Text #19

Max Range: 0.2803. Min Range: -0.2803

Max Act: 0.2081. Min Act: -0.0000

Data Index: 968972 (The Pile)

Max Activating Token Index: 271