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

Dataset: The Pile

Neuron 673 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: 1.6796. Min Range: -1.6796

Max Act: 1.6796. Min Act: -0.0000

Data Index: 745860 (The Pile)

Max Activating Token Index: 196

Text #1

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.3012. Min Act: -0.0000

Data Index: 1960844 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.2867. Min Act: -0.0000

Data Index: 174330 (The Pile)

Max Activating Token Index: 151

Text #3

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.3609. Min Act: -0.0000

Data Index: 1689249 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.2754. Min Act: -0.0000

Data Index: 1237705 (The Pile)

Max Activating Token Index: 653

Text #5

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.2358. Min Act: -0.0000

Data Index: 1373448 (The Pile)

Max Activating Token Index: 696

Text #6

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1682. Min Act: -0.0000

Data Index: 877913 (The Pile)

Max Activating Token Index: 36

Text #7

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1310. Min Act: -0.0000

Data Index: 1652660 (The Pile)

Max Activating Token Index: 379

Text #8

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1204. Min Act: -0.0000

Data Index: 857794 (The Pile)

Max Activating Token Index: 267

Text #9

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.2384. Min Act: -0.0000

Data Index: 561756 (The Pile)

Max Activating Token Index: 769

Text #10

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1638. Min Act: -0.0000

Data Index: 499265 (The Pile)

Max Activating Token Index: 835

Text #11

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.3093. Min Act: -0.0000

Data Index: 804680 (The Pile)

Max Activating Token Index: 192

Text #12

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1526. Min Act: -0.0000

Data Index: 1763463 (The Pile)

Max Activating Token Index: 155

Text #13

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1237. Min Act: -0.0000

Data Index: 437305 (The Pile)

Max Activating Token Index: 748

Text #14

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.0708. Min Act: -0.0000

Data Index: 624067 (The Pile)

Max Activating Token Index: 419

Text #15

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1810. Min Act: -0.0000

Data Index: 1504106 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 1.6796. Min Range: -1.6796

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1024749 (The Pile)

Max Activating Token Index: 981

Text #17

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1860448 (The Pile)

Max Activating Token Index: 312

Text #18

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1135. Min Act: -0.0000

Data Index: 387915 (The Pile)

Max Activating Token Index: 536

Text #19

Max Range: 1.6796. Min Range: -1.6796

Max Act: 1.1021. Min Act: -0.0000

Data Index: 773783 (The Pile)

Max Activating Token Index: 84