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

Dataset: The Pile

Neuron 1692 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: 0.2556. Min Range: -0.2556

Max Act: 0.2556. Min Act: -0.0000

Data Index: 1648563 (The Pile)

Max Activating Token Index: 398

Text #1

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2208. Min Act: -0.0000

Data Index: 503542 (The Pile)

Max Activating Token Index: 713

Text #2

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2277. Min Act: -0.0000

Data Index: 38706 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2447. Min Act: -0.0000

Data Index: 533515 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2346. Min Act: -0.0000

Data Index: 1319189 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2283. Min Act: -0.0000

Data Index: 1965968 (The Pile)

Max Activating Token Index: 608

Text #6

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2184. Min Act: -0.0000

Data Index: 959981 (The Pile)

Max Activating Token Index: 651

Text #7

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2014. Min Act: -0.0000

Data Index: 829113 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2210. Min Act: -0.0000

Data Index: 1703071 (The Pile)

Max Activating Token Index: 516

Text #9

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2050. Min Act: -0.0000

Data Index: 335615 (The Pile)

Max Activating Token Index: 107

Text #10

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2422. Min Act: -0.0000

Data Index: 1465818 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2185. Min Act: -0.0000

Data Index: 1753100 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2245. Min Act: -0.0000

Data Index: 672351 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2061. Min Act: -0.0000

Data Index: 982348 (The Pile)

Max Activating Token Index: 322

Text #14

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2074. Min Act: -0.0000

Data Index: 1727760 (The Pile)

Max Activating Token Index: 494

Text #15

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1933097 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1991. Min Act: -0.0000

Data Index: 5309 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1594670 (The Pile)

Max Activating Token Index: 595

Text #18

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.1924. Min Act: -0.0000

Data Index: 210869 (The Pile)

Max Activating Token Index: 675

Text #19

Max Range: 0.2556. Min Range: -0.2556

Max Act: 0.2060. Min Act: -0.0000

Data Index: 943843 (The Pile)

Max Activating Token Index: 900