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

Dataset: The Pile

Neuron 3675 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.8544. Min Act: -0.0000

Data Index: 1301939 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1632433 (The Pile)

Max Activating Token Index: 234

Text #2

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.6174. Min Act: -0.0000

Data Index: 872758 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.5086. Min Act: -0.0000

Data Index: 1504206 (The Pile)

Max Activating Token Index: 826

Text #4

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3702. Min Act: -0.0000

Data Index: 922691 (The Pile)

Max Activating Token Index: 811

Text #5

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.2938. Min Act: -0.0000

Data Index: 17318 (The Pile)

Max Activating Token Index: 896

Text #6

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.4004. Min Act: -0.0000

Data Index: 183368 (The Pile)

Max Activating Token Index: 469

Text #7

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3382. Min Act: -0.0000

Data Index: 432676 (The Pile)

Max Activating Token Index: 999

Text #8

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3478. Min Act: -0.0000

Data Index: 46670 (The Pile)

Max Activating Token Index: 360

Text #9

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3108. Min Act: -0.0000

Data Index: 1278477 (The Pile)

Max Activating Token Index: 875

Text #10

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.2981. Min Act: -0.0000

Data Index: 508408 (The Pile)

Max Activating Token Index: 812

Text #11

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3433. Min Act: -0.0000

Data Index: 860138 (The Pile)

Max Activating Token Index: 888

Text #12

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3196. Min Act: -0.0000

Data Index: 1120163 (The Pile)

Max Activating Token Index: 917

Text #13

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.2854. Min Act: -0.0000

Data Index: 756671 (The Pile)

Max Activating Token Index: 457

Text #14

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3447. Min Act: -0.0000

Data Index: 1832515 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.2897. Min Act: -0.0000

Data Index: 1004368 (The Pile)

Max Activating Token Index: 974

Text #16

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.3091. Min Act: -0.0000

Data Index: 799409 (The Pile)

Max Activating Token Index: 757

Text #17

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.2793. Min Act: -0.0000

Data Index: 1678963 (The Pile)

Max Activating Token Index: 618

Text #18

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.2697. Min Act: -0.0000

Data Index: 1615188 (The Pile)

Max Activating Token Index: 898

Text #19

Max Range: 0.8544. Min Range: -0.8544

Max Act: 0.2124. Min Act: -0.0000

Data Index: 1848912 (The Pile)

Max Activating Token Index: 838