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

Dataset: The Pile

Neuron 2279 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: 0.8888. Min Range: -0.8888

Max Act: 0.8888. Min Act: -0.0000

Data Index: 1174393 (The Pile)

Max Activating Token Index: 235

Text #1

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.7865. Min Act: -0.0000

Data Index: 1771990 (The Pile)

Max Activating Token Index: 305

Text #2

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1687904 (The Pile)

Max Activating Token Index: 304

Text #3

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6934. Min Act: -0.0000

Data Index: 973410 (The Pile)

Max Activating Token Index: 13

Text #4

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6950. Min Act: -0.0000

Data Index: 986491 (The Pile)

Max Activating Token Index: 809

Text #5

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6283. Min Act: -0.0000

Data Index: 577366 (The Pile)

Max Activating Token Index: 789

Text #6

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6259. Min Act: -0.0000

Data Index: 1139458 (The Pile)

Max Activating Token Index: 1012

Text #7

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6070. Min Act: -0.0001

Data Index: 436651 (The Pile)

Max Activating Token Index: 254

Text #8

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5987. Min Act: -0.0000

Data Index: 578786 (The Pile)

Max Activating Token Index: 452

Text #9

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5970. Min Act: -0.0000

Data Index: 1282387 (The Pile)

Max Activating Token Index: 455

Text #10

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5875. Min Act: -0.0000

Data Index: 1523527 (The Pile)

Max Activating Token Index: 476

Text #11

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1083274 (The Pile)

Max Activating Token Index: 462

Text #12

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5347. Min Act: -0.0000

Data Index: 252672 (The Pile)

Max Activating Token Index: 762

Text #13

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1360380 (The Pile)

Max Activating Token Index: 380

Text #14

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5635. Min Act: -0.0000

Data Index: 60361 (The Pile)

Max Activating Token Index: 137

Text #15

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5776. Min Act: -0.0000

Data Index: 482806 (The Pile)

Max Activating Token Index: 69

Text #16

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5811. Min Act: -0.0000

Data Index: 1728986 (The Pile)

Max Activating Token Index: 934

Text #17

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5584. Min Act: -0.0000

Data Index: 526659 (The Pile)

Max Activating Token Index: 97

Text #18

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5780. Min Act: -0.0000

Data Index: 1292441 (The Pile)

Max Activating Token Index: 258

Text #19

Max Range: 0.8888. Min Range: -0.8888

Max Act: 0.5819. Min Act: -0.0000

Data Index: 167677 (The Pile)

Max Activating Token Index: 797