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

Dataset: The Pile

Neuron 4431 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: 0.3035. Min Range: -0.3035

Max Act: 0.3035. Min Act: -0.0000

Data Index: 662448 (The Pile)

Max Activating Token Index: 228

Text #1

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2425. Min Act: -0.0000

Data Index: 1358711 (The Pile)

Max Activating Token Index: 117

Text #2

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2355. Min Act: -0.0000

Data Index: 1743578 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2331. Min Act: -0.0000

Data Index: 1790699 (The Pile)

Max Activating Token Index: 205

Text #4

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1792991 (The Pile)

Max Activating Token Index: 51

Text #5

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1980. Min Act: -0.0000

Data Index: 130484 (The Pile)

Max Activating Token Index: 878

Text #6

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2215. Min Act: -0.0000

Data Index: 1176255 (The Pile)

Max Activating Token Index: 1016

Text #7

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2108. Min Act: -0.0000

Data Index: 1506033 (The Pile)

Max Activating Token Index: 132

Text #8

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2150. Min Act: -0.0000

Data Index: 269157 (The Pile)

Max Activating Token Index: 663

Text #9

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1991. Min Act: -0.0000

Data Index: 632687 (The Pile)

Max Activating Token Index: 701

Text #10

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2036. Min Act: -0.0000

Data Index: 1939308 (The Pile)

Max Activating Token Index: 40

Text #11

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1555476 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1191717 (The Pile)

Max Activating Token Index: 405

Text #13

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1772073 (The Pile)

Max Activating Token Index: 298

Text #14

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.2000. Min Act: -0.0000

Data Index: 1365763 (The Pile)

Max Activating Token Index: 965

Text #15

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1987. Min Act: -0.0000

Data Index: 763011 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1859. Min Act: -0.0000

Data Index: 1014910 (The Pile)

Max Activating Token Index: 292

Text #17

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1911. Min Act: -0.0000

Data Index: 1522756 (The Pile)

Max Activating Token Index: 281

Text #18

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1854. Min Act: -0.0000

Data Index: 1423073 (The Pile)

Max Activating Token Index: 297

Text #19

Max Range: 0.3035. Min Range: -0.3035

Max Act: 0.1876. Min Act: -0.0000

Data Index: 1834184 (The Pile)

Max Activating Token Index: 153