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

Dataset: The Pile

Neuron 2543 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2289. Min Act: -0.0000

Data Index: 1905176 (The Pile)

Max Activating Token Index: 676

Text #1

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1200872 (The Pile)

Max Activating Token Index: 810

Text #2

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2134. Min Act: -0.0000

Data Index: 330503 (The Pile)

Max Activating Token Index: 197

Text #3

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1858. Min Act: -0.0000

Data Index: 924282 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2041. Min Act: -0.0000

Data Index: 784523 (The Pile)

Max Activating Token Index: 139

Text #5

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2066. Min Act: -0.0000

Data Index: 112450 (The Pile)

Max Activating Token Index: 887

Text #6

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1278874 (The Pile)

Max Activating Token Index: 539

Text #7

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1902. Min Act: -0.0000

Data Index: 1469681 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1802791 (The Pile)

Max Activating Token Index: 294

Text #9

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2120. Min Act: -0.0000

Data Index: 1585972 (The Pile)

Max Activating Token Index: 462

Text #10

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2039. Min Act: -0.0000

Data Index: 13766 (The Pile)

Max Activating Token Index: 757

Text #11

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2009. Min Act: -0.0000

Data Index: 1270958 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2042. Min Act: -0.0000

Data Index: 1447164 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1913. Min Act: -0.0000

Data Index: 630553 (The Pile)

Max Activating Token Index: 788

Text #14

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1967. Min Act: -0.0000

Data Index: 1019492 (The Pile)

Max Activating Token Index: 861

Text #15

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2094. Min Act: -0.0000

Data Index: 184190 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1805. Min Act: -0.0000

Data Index: 1937156 (The Pile)

Max Activating Token Index: 941

Text #17

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.1757. Min Act: -0.0000

Data Index: 1296390 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2035. Min Act: -0.0000

Data Index: 73689 (The Pile)

Max Activating Token Index: 376

Text #19

Max Range: 0.2331. Min Range: -0.2331

Max Act: 0.2066. Min Act: -0.0000

Data Index: 1601031 (The Pile)

Max Activating Token Index: 444