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

Dataset: The Pile

Neuron 4695 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: 1.5587. Min Range: -1.5587

Max Act: 1.5587. Min Act: -0.0000

Data Index: 1092618 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.5276. Min Act: -0.0000

Data Index: 279257 (The Pile)

Max Activating Token Index: 21

Text #2

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.5234. Min Act: -0.0000

Data Index: 858425 (The Pile)

Max Activating Token Index: 743

Text #3

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.5073. Min Act: -0.0000

Data Index: 365015 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.4022. Min Act: -0.0000

Data Index: 1484628 (The Pile)

Max Activating Token Index: 136

Text #5

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.4306. Min Act: -0.0000

Data Index: 1117480 (The Pile)

Max Activating Token Index: 33

Text #6

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1520034 (The Pile)

Max Activating Token Index: 754

Text #7

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.4100. Min Act: -0.0000

Data Index: 484440 (The Pile)

Max Activating Token Index: 954

Text #8

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.3907. Min Act: -0.0000

Data Index: 696118 (The Pile)

Max Activating Token Index: 559

Text #9

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.4352. Min Act: -0.0000

Data Index: 1622606 (The Pile)

Max Activating Token Index: 652

Text #10

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.3587. Min Act: -0.0000

Data Index: 1666500 (The Pile)

Max Activating Token Index: 200

Text #11

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.4172. Min Act: -0.0000

Data Index: 1333351 (The Pile)

Max Activating Token Index: 451

Text #12

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.3355. Min Act: -0.0000

Data Index: 217659 (The Pile)

Max Activating Token Index: 20

Text #13

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.3277. Min Act: -0.0000

Data Index: 943238 (The Pile)

Max Activating Token Index: 183

Text #14

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.2236. Min Act: -0.0000

Data Index: 180019 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.2863. Min Act: -0.0000

Data Index: 127905 (The Pile)

Max Activating Token Index: 251

Text #16

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.2709. Min Act: -0.0000

Data Index: 613635 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.2650. Min Act: -0.0000

Data Index: 1385296 (The Pile)

Max Activating Token Index: 212

Text #18

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.1955. Min Act: -0.0000

Data Index: 640375 (The Pile)

Max Activating Token Index: 780

Text #19

Max Range: 1.5587. Min Range: -1.5587

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1113925 (The Pile)

Max Activating Token Index: 62