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

Dataset: The Pile

Neuron 3060 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: 0.9976. Min Range: -0.9976

Max Act: 0.9976. Min Act: -0.0000

Data Index: 1967423 (The Pile)

Max Activating Token Index: 886

Text #1

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9725. Min Act: -0.0000

Data Index: 181215 (The Pile)

Max Activating Token Index: 442

Text #2

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9333. Min Act: -0.0000

Data Index: 1783765 (The Pile)

Max Activating Token Index: 14

Text #3

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8566. Min Act: -0.0000

Data Index: 1749633 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9120. Min Act: -0.0001

Data Index: 88215 (The Pile)

Max Activating Token Index: 839

Text #5

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8992. Min Act: -0.0000

Data Index: 530991 (The Pile)

Max Activating Token Index: 196

Text #6

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8444. Min Act: -0.0000

Data Index: 949394 (The Pile)

Max Activating Token Index: 442

Text #7

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8827. Min Act: -0.0000

Data Index: 996914 (The Pile)

Max Activating Token Index: 522

Text #8

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9228. Min Act: -0.0000

Data Index: 774820 (The Pile)

Max Activating Token Index: 496

Text #9

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.9205. Min Act: -0.0000

Data Index: 1058539 (The Pile)

Max Activating Token Index: 494

Text #10

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8442. Min Act: -0.0000

Data Index: 119969 (The Pile)

Max Activating Token Index: 827

Text #11

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8226. Min Act: -0.0000

Data Index: 65659 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8187. Min Act: -0.0000

Data Index: 1341543 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8022. Min Act: -0.0000

Data Index: 1992289 (The Pile)

Max Activating Token Index: 554

Text #14

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7665. Min Act: -0.0000

Data Index: 1998637 (The Pile)

Max Activating Token Index: 1002

Text #15

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.8542. Min Act: -0.0000

Data Index: 777016 (The Pile)

Max Activating Token Index: 876

Text #16

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7757. Min Act: -0.0000

Data Index: 1642661 (The Pile)

Max Activating Token Index: 647

Text #17

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7975. Min Act: -0.0000

Data Index: 1206498 (The Pile)

Max Activating Token Index: 987

Text #18

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7368. Min Act: -0.0001

Data Index: 838197 (The Pile)

Max Activating Token Index: 582

Text #19

Max Range: 0.9976. Min Range: -0.9976

Max Act: 0.7746. Min Act: -0.0000

Data Index: 369684 (The Pile)

Max Activating Token Index: 172