Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2202 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6984. Min Act: -0.0000

Data Index: 663255 (The Pile)

Max Activating Token Index: 338

Text #1

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6412. Min Act: -0.0000

Data Index: 1761505 (The Pile)

Max Activating Token Index: 814

Text #2

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.6227. Min Act: -0.0000

Data Index: 1503262 (The Pile)

Max Activating Token Index: 59

Text #3

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5324. Min Act: -0.0000

Data Index: 1758245 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5328. Min Act: -0.0000

Data Index: 127718 (The Pile)

Max Activating Token Index: 28

Text #5

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5083. Min Act: -0.0000

Data Index: 1432583 (The Pile)

Max Activating Token Index: 208

Text #6

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5350. Min Act: -0.0000

Data Index: 471559 (The Pile)

Max Activating Token Index: 51

Text #7

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5319. Min Act: -0.0000

Data Index: 1968697 (The Pile)

Max Activating Token Index: 14

Text #8

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5337. Min Act: -0.0000

Data Index: 122050 (The Pile)

Max Activating Token Index: 119

Text #9

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5023. Min Act: -0.0000

Data Index: 1371557 (The Pile)

Max Activating Token Index: 835

Text #10

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5161. Min Act: -0.0000

Data Index: 1348730 (The Pile)

Max Activating Token Index: 29

Text #11

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5075. Min Act: -0.0001

Data Index: 900525 (The Pile)

Max Activating Token Index: 350

Text #12

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5220. Min Act: -0.0000

Data Index: 1012295 (The Pile)

Max Activating Token Index: 182

Text #13

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1345934 (The Pile)

Max Activating Token Index: 34

Text #14

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1507580 (The Pile)

Max Activating Token Index: 586

Text #15

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.4856. Min Act: -0.0000

Data Index: 814496 (The Pile)

Max Activating Token Index: 266

Text #16

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.4994. Min Act: -0.0000

Data Index: 450328 (The Pile)

Max Activating Token Index: 698

Text #17

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1818787 (The Pile)

Max Activating Token Index: 634

Text #18

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.4786. Min Act: -0.0000

Data Index: 220701 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 0.6984. Min Range: -0.6984

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1915761 (The Pile)

Max Activating Token Index: 695