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

Dataset: The Pile

Neuron 3029 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.8168. Min Act: -0.0000

Data Index: 253868 (The Pile)

Max Activating Token Index: 527

Text #1

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7527. Min Act: -0.0000

Data Index: 1576633 (The Pile)

Max Activating Token Index: 500

Text #2

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7243. Min Act: -0.0000

Data Index: 1963602 (The Pile)

Max Activating Token Index: 104

Text #3

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.7037. Min Act: -0.0000

Data Index: 1672909 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6479. Min Act: -0.0000

Data Index: 824404 (The Pile)

Max Activating Token Index: 720

Text #5

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6289. Min Act: -0.0000

Data Index: 569882 (The Pile)

Max Activating Token Index: 668

Text #6

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5788. Min Act: -0.0000

Data Index: 1962033 (The Pile)

Max Activating Token Index: 958

Text #7

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1712528 (The Pile)

Max Activating Token Index: 305

Text #8

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5805. Min Act: -0.0000

Data Index: 135565 (The Pile)

Max Activating Token Index: 300

Text #9

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5830. Min Act: -0.0000

Data Index: 895496 (The Pile)

Max Activating Token Index: 73

Text #10

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1516805 (The Pile)

Max Activating Token Index: 832

Text #11

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5875. Min Act: -0.0000

Data Index: 101300 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5505. Min Act: -0.0000

Data Index: 1105818 (The Pile)

Max Activating Token Index: 126

Text #13

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5673. Min Act: -0.0000

Data Index: 743274 (The Pile)

Max Activating Token Index: 435

Text #14

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5622. Min Act: -0.0000

Data Index: 1559807 (The Pile)

Max Activating Token Index: 102

Text #15

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5842. Min Act: -0.0000

Data Index: 1967095 (The Pile)

Max Activating Token Index: 729

Text #16

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5719. Min Act: -0.0000

Data Index: 1505023 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5755. Min Act: -0.0000

Data Index: 1809830 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5533. Min Act: -0.0000

Data Index: 598041 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.8168. Min Range: -0.8168

Max Act: 0.5359. Min Act: -0.0000

Data Index: 1942038 (The Pile)

Max Activating Token Index: 634