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

Dataset: The Pile

Neuron 4050 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0688. Min Act: -0.0000

Data Index: 961260 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0664. Min Act: 0.0000

Data Index: 527868 (The Pile)

Max Activating Token Index: 29

Text #2

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0667. Min Act: -0.0000

Data Index: 178404 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0542. Min Act: 0.0000

Data Index: 1120828 (The Pile)

Max Activating Token Index: 130

Text #4

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0489. Min Act: 0.0000

Data Index: 206779 (The Pile)

Max Activating Token Index: 1023

Text #5

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0474. Min Act: 0.0000

Data Index: 36444 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0449. Min Act: -0.0000

Data Index: 1821135 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0466. Min Act: 0.0000

Data Index: 870259 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0448. Min Act: 0.0000

Data Index: 1906904 (The Pile)

Max Activating Token Index: 971

Text #9

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0463. Min Act: 0.0000

Data Index: 23348 (The Pile)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0460. Min Act: 0.0000

Data Index: 1351394 (The Pile)

Max Activating Token Index: 119

Text #11

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0449. Min Act: 0.0000

Data Index: 320202 (The Pile)

Max Activating Token Index: 1023

Text #12

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0449. Min Act: 0.0000

Data Index: 1490303 (The Pile)

Max Activating Token Index: 293

Text #13

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0449. Min Act: 0.0000

Data Index: 1908661 (The Pile)

Max Activating Token Index: 636

Text #14

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0442. Min Act: -0.0000

Data Index: 1758018 (The Pile)

Max Activating Token Index: 971

Text #15

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0440. Min Act: 0.0000

Data Index: 251399 (The Pile)

Max Activating Token Index: 137

Text #16

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0436. Min Act: 0.0000

Data Index: 1760376 (The Pile)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0435. Min Act: 0.0000

Data Index: 1168342 (The Pile)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0436. Min Act: 0.0000

Data Index: 25990 (The Pile)

Max Activating Token Index: 1023

Text #19

Max Range: 0.0688. Min Range: -0.0688

Max Act: 0.0434. Min Act: 0.0000

Data Index: 1153023 (The Pile)

Max Activating Token Index: 1023