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

Dataset: The Pile

Neuron 897 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.3168. Min Act: -0.0000

Data Index: 1864555 (The Pile)

Max Activating Token Index: 142

Text #1

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2922. Min Act: -0.0000

Data Index: 1554734 (The Pile)

Max Activating Token Index: 101

Text #2

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2154. Min Act: -0.0000

Data Index: 679287 (The Pile)

Max Activating Token Index: 892

Text #3

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1648540 (The Pile)

Max Activating Token Index: 832

Text #4

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1042639 (The Pile)

Max Activating Token Index: 851

Text #5

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2349. Min Act: -0.0000

Data Index: 518295 (The Pile)

Max Activating Token Index: 250

Text #6

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2054. Min Act: -0.0000

Data Index: 131654 (The Pile)

Max Activating Token Index: 795

Text #7

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2265. Min Act: -0.0000

Data Index: 1103145 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2303. Min Act: -0.0000

Data Index: 382942 (The Pile)

Max Activating Token Index: 623

Text #9

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2261. Min Act: -0.0000

Data Index: 395646 (The Pile)

Max Activating Token Index: 973

Text #10

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2165. Min Act: -0.0000

Data Index: 654112 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2183. Min Act: -0.0000

Data Index: 1434583 (The Pile)

Max Activating Token Index: 691

Text #12

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1513136 (The Pile)

Max Activating Token Index: 776

Text #13

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2023. Min Act: -0.0000

Data Index: 128341 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2049. Min Act: -0.0000

Data Index: 169402 (The Pile)

Max Activating Token Index: 889

Text #15

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2023. Min Act: -0.0000

Data Index: 362310 (The Pile)

Max Activating Token Index: 757

Text #16

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2046. Min Act: -0.0000

Data Index: 1452543 (The Pile)

Max Activating Token Index: 371

Text #17

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2008. Min Act: -0.0000

Data Index: 443510 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1992770 (The Pile)

Max Activating Token Index: 867

Text #19

Max Range: 0.3168. Min Range: -0.3168

Max Act: 0.1972. Min Act: -0.0000

Data Index: 361793 (The Pile)

Max Activating Token Index: 961