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

Dataset: The Pile

Neuron 2986 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: 0.8232. Min Range: -0.8232

Max Act: 0.8232. Min Act: -0.0000

Data Index: 27875 (The Pile)

Max Activating Token Index: 834

Text #1

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1890901 (The Pile)

Max Activating Token Index: 1016

Text #2

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5605. Min Act: -0.0000

Data Index: 1782870 (The Pile)

Max Activating Token Index: 849

Text #3

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5857. Min Act: -0.0000

Data Index: 1078835 (The Pile)

Max Activating Token Index: 878

Text #4

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5364. Min Act: -0.0000

Data Index: 107993 (The Pile)

Max Activating Token Index: 967

Text #5

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5305. Min Act: -0.0000

Data Index: 633896 (The Pile)

Max Activating Token Index: 339

Text #6

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5298. Min Act: -0.0000

Data Index: 1047800 (The Pile)

Max Activating Token Index: 953

Text #7

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5091. Min Act: -0.0000

Data Index: 922106 (The Pile)

Max Activating Token Index: 595

Text #8

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1926636 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1478285 (The Pile)

Max Activating Token Index: 833

Text #10

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5107. Min Act: -0.0000

Data Index: 472311 (The Pile)

Max Activating Token Index: 147

Text #11

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5190. Min Act: -0.0000

Data Index: 1098479 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.5001. Min Act: -0.0000

Data Index: 1605855 (The Pile)

Max Activating Token Index: 57

Text #13

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4982. Min Act: -0.0000

Data Index: 1382401 (The Pile)

Max Activating Token Index: 959

Text #14

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4982. Min Act: -0.0000

Data Index: 56003 (The Pile)

Max Activating Token Index: 936

Text #15

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4932. Min Act: -0.0000

Data Index: 556025 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4858. Min Act: -0.0000

Data Index: 749321 (The Pile)

Max Activating Token Index: 999

Text #17

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4727. Min Act: -0.0000

Data Index: 1926882 (The Pile)

Max Activating Token Index: 388

Text #18

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1977020 (The Pile)

Max Activating Token Index: 44

Text #19

Max Range: 0.8232. Min Range: -0.8232

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1732291 (The Pile)

Max Activating Token Index: 469