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

Dataset: The Pile

Neuron 198 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.5207. Min Act: -0.0000

Data Index: 595716 (The Pile)

Max Activating Token Index: 637

Text #1

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.2242. Min Act: -0.0000

Data Index: 1061270 (The Pile)

Max Activating Token Index: 770

Text #2

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.3326. Min Act: -0.0000

Data Index: 100561 (The Pile)

Max Activating Token Index: 329

Text #3

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.1628. Min Act: -0.0000

Data Index: 244832 (The Pile)

Max Activating Token Index: 664

Text #4

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.3010. Min Act: -0.0000

Data Index: 1607121 (The Pile)

Max Activating Token Index: 755

Text #5

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.0378. Min Act: -0.0000

Data Index: 370257 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.1146. Min Act: -0.0000

Data Index: 925491 (The Pile)

Max Activating Token Index: 681

Text #7

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.8710. Min Act: -0.0000

Data Index: 1402521 (The Pile)

Max Activating Token Index: 137

Text #8

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.1148. Min Act: -0.0000

Data Index: 131275 (The Pile)

Max Activating Token Index: 615

Text #9

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.2455. Min Act: -0.0000

Data Index: 1580749 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.0934. Min Act: -0.0000

Data Index: 1846608 (The Pile)

Max Activating Token Index: 388

Text #11

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.0892. Min Act: -0.0000

Data Index: 656686 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.0740. Min Act: -0.0000

Data Index: 344119 (The Pile)

Max Activating Token Index: 152

Text #13

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.0480. Min Act: -0.0000

Data Index: 151804 (The Pile)

Max Activating Token Index: 1020

Text #14

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.0655. Min Act: -0.0000

Data Index: 845193 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.1818. Min Act: -0.0000

Data Index: 1523640 (The Pile)

Max Activating Token Index: 49

Text #16

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.8813. Min Act: -0.0000

Data Index: 1068026 (The Pile)

Max Activating Token Index: 599

Text #17

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.0234. Min Act: -0.0000

Data Index: 342812 (The Pile)

Max Activating Token Index: 656

Text #18

Max Range: 3.5207. Min Range: -3.5207

Max Act: 3.1684. Min Act: -0.0000

Data Index: 476055 (The Pile)

Max Activating Token Index: 753

Text #19

Max Range: 3.5207. Min Range: -3.5207

Max Act: 2.9977. Min Act: -0.0000

Data Index: 1039727 (The Pile)

Max Activating Token Index: 63