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

Dataset: The Pile

Neuron 2800 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: -0.0000

Data Index: 595975 (The Pile)

Max Activating Token Index: 265

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1102. Min Act: -0.0000

Data Index: 722044 (The Pile)

Max Activating Token Index: 277

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1062. Min Act: -0.0000

Data Index: 173612 (The Pile)

Max Activating Token Index: 462

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1104. Min Act: -0.0000

Data Index: 1967518 (The Pile)

Max Activating Token Index: 307

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1078. Min Act: -0.0000

Data Index: 992988 (The Pile)

Max Activating Token Index: 492

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1065. Min Act: -0.0000

Data Index: 357012 (The Pile)

Max Activating Token Index: 171

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1994498 (The Pile)

Max Activating Token Index: 52

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1118. Min Act: -0.0000

Data Index: 579088 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1050. Min Act: -0.0000

Data Index: 876919 (The Pile)

Max Activating Token Index: 548

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1041. Min Act: -0.0000

Data Index: 344586 (The Pile)

Max Activating Token Index: 395

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1012. Min Act: -0.0000

Data Index: 1227445 (The Pile)

Max Activating Token Index: 480

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0919. Min Act: -0.0000

Data Index: 419347 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1083. Min Act: -0.0000

Data Index: 330648 (The Pile)

Max Activating Token Index: 388

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0959. Min Act: -0.0000

Data Index: 1950416 (The Pile)

Max Activating Token Index: 537

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1058. Min Act: -0.0000

Data Index: 1098665 (The Pile)

Max Activating Token Index: 463

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1008. Min Act: -0.0000

Data Index: 634897 (The Pile)

Max Activating Token Index: 499

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1065934 (The Pile)

Max Activating Token Index: 185

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0977. Min Act: -0.0000

Data Index: 1831192 (The Pile)

Max Activating Token Index: 790

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1028. Min Act: -0.0000

Data Index: 342945 (The Pile)

Max Activating Token Index: 728

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1509374 (The Pile)

Max Activating Token Index: 560