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

Dataset: The Pile

Neuron 4637 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.3106. Min Act: -0.0000

Data Index: 1572832 (The Pile)

Max Activating Token Index: 329

Text #1

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.2217. Min Act: -0.0000

Data Index: 1161561 (The Pile)

Max Activating Token Index: 701

Text #2

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1645. Min Act: -0.0000

Data Index: 642786 (The Pile)

Max Activating Token Index: 943

Text #3

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1103. Min Act: -0.0000

Data Index: 1707850 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.1002. Min Act: -0.0000

Data Index: 1531534 (The Pile)

Max Activating Token Index: 971

Text #5

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0639. Min Act: -0.0000

Data Index: 220328 (The Pile)

Max Activating Token Index: 620

Text #6

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0662. Min Act: -0.0000

Data Index: 57703 (The Pile)

Max Activating Token Index: 493

Text #7

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0485. Min Act: -0.0000

Data Index: 1013198 (The Pile)

Max Activating Token Index: 641

Text #8

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0023. Min Act: -0.0000

Data Index: 980602 (The Pile)

Max Activating Token Index: 648

Text #9

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0092. Min Act: -0.0000

Data Index: 792203 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 1.3106. Min Range: -1.3106

Max Act: 0.9461. Min Act: -0.0000

Data Index: 1380862 (The Pile)

Max Activating Token Index: 839

Text #11

Max Range: 1.3106. Min Range: -1.3106

Max Act: 0.9993. Min Act: -0.0000

Data Index: 1758094 (The Pile)

Max Activating Token Index: 195

Text #12

Max Range: 1.3106. Min Range: -1.3106

Max Act: 0.9751. Min Act: -0.0000

Data Index: 1110237 (The Pile)

Max Activating Token Index: 337

Text #13

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0101. Min Act: -0.0000

Data Index: 1651994 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0226. Min Act: -0.0000

Data Index: 1159497 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 1.3106. Min Range: -1.3106

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1558796 (The Pile)

Max Activating Token Index: 798

Text #16

Max Range: 1.3106. Min Range: -1.3106

Max Act: 0.9853. Min Act: -0.0000

Data Index: 1110701 (The Pile)

Max Activating Token Index: 407

Text #17

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0088. Min Act: -0.0000

Data Index: 1663317 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 1.3106. Min Range: -1.3106

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1973919 (The Pile)

Max Activating Token Index: 324

Text #19

Max Range: 1.3106. Min Range: -1.3106

Max Act: 0.9468. Min Act: -0.0000

Data Index: 621200 (The Pile)

Max Activating Token Index: 141