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

Dataset: The Pile

Neuron 720 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: 1.4110. Min Range: -1.4110

Max Act: 1.4110. Min Act: -0.0000

Data Index: 162780 (The Pile)

Max Activating Token Index: 129

Text #1

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1650535 (The Pile)

Max Activating Token Index: 104

Text #2

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1041496 (The Pile)

Max Activating Token Index: 224

Text #3

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8508. Min Act: -0.0000

Data Index: 725359 (The Pile)

Max Activating Token Index: 715

Text #4

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8474. Min Act: -0.0000

Data Index: 1371124 (The Pile)

Max Activating Token Index: 82

Text #5

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8509. Min Act: -0.0000

Data Index: 1288950 (The Pile)

Max Activating Token Index: 714

Text #6

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1156593 (The Pile)

Max Activating Token Index: 83

Text #7

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8350. Min Act: -0.0000

Data Index: 1918233 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8869. Min Act: -0.0000

Data Index: 1763950 (The Pile)

Max Activating Token Index: 480

Text #9

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.7873. Min Act: -0.0000

Data Index: 1845367 (The Pile)

Max Activating Token Index: 191

Text #10

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8925. Min Act: -0.0000

Data Index: 921231 (The Pile)

Max Activating Token Index: 54

Text #11

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8281. Min Act: -0.0000

Data Index: 1036611 (The Pile)

Max Activating Token Index: 581

Text #12

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8213. Min Act: -0.0000

Data Index: 1578464 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.9201. Min Act: -0.0000

Data Index: 32829 (The Pile)

Max Activating Token Index: 982

Text #14

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8194. Min Act: -0.0000

Data Index: 342029 (The Pile)

Max Activating Token Index: 194

Text #15

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1950217 (The Pile)

Max Activating Token Index: 954

Text #16

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8047. Min Act: -0.0000

Data Index: 291501 (The Pile)

Max Activating Token Index: 566

Text #17

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1182183 (The Pile)

Max Activating Token Index: 279

Text #18

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.7609. Min Act: -0.0000

Data Index: 337593 (The Pile)

Max Activating Token Index: 408

Text #19

Max Range: 1.4110. Min Range: -1.4110

Max Act: 0.7603. Min Act: -0.0000

Data Index: 1585519 (The Pile)

Max Activating Token Index: 569