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

Dataset: The Pile

Neuron 1361 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: 0.5168. Min Range: -0.5168

Max Act: 0.5045. Min Act: -0.0000

Data Index: 1863612 (The Pile)

Max Activating Token Index: 1023

Text #1

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4578. Min Act: -0.0000

Data Index: 1033320 (The Pile)

Max Activating Token Index: 743

Text #2

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.5168. Min Act: -0.0000

Data Index: 481526 (The Pile)

Max Activating Token Index: 970

Text #3

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4412. Min Act: -0.0000

Data Index: 1801212 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1437234 (The Pile)

Max Activating Token Index: 233

Text #5

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4227. Min Act: -0.0000

Data Index: 472368 (The Pile)

Max Activating Token Index: 872

Text #6

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4076. Min Act: -0.0000

Data Index: 71732 (The Pile)

Max Activating Token Index: 436

Text #7

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1214780 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4106. Min Act: -0.0000

Data Index: 1130617 (The Pile)

Max Activating Token Index: 778

Text #9

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.4028. Min Act: -0.0000

Data Index: 1011878 (The Pile)

Max Activating Token Index: 585

Text #10

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3866. Min Act: -0.0000

Data Index: 407832 (The Pile)

Max Activating Token Index: 963

Text #11

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3945. Min Act: -0.0000

Data Index: 711868 (The Pile)

Max Activating Token Index: 107

Text #12

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3824. Min Act: -0.0000

Data Index: 1853522 (The Pile)

Max Activating Token Index: 758

Text #13

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3868. Min Act: -0.0000

Data Index: 503806 (The Pile)

Max Activating Token Index: 557

Text #14

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3992. Min Act: -0.0000

Data Index: 1480446 (The Pile)

Max Activating Token Index: 314

Text #15

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3948. Min Act: -0.0000

Data Index: 1083362 (The Pile)

Max Activating Token Index: 640

Text #16

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3862. Min Act: -0.0000

Data Index: 1129051 (The Pile)

Max Activating Token Index: 372

Text #17

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3682. Min Act: -0.0000

Data Index: 1249202 (The Pile)

Max Activating Token Index: 812

Text #18

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3777. Min Act: -0.0000

Data Index: 1533317 (The Pile)

Max Activating Token Index: 524

Text #19

Max Range: 0.5168. Min Range: -0.5168

Max Act: 0.3884. Min Act: -0.0000

Data Index: 243302 (The Pile)

Max Activating Token Index: 370