Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3587 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.0130. Min Range: -1.0130

Max Act: 1.0130. Min Act: -0.0000

Data Index: 659041 (The Pile)

Max Activating Token Index: 143

Text #1

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.9623. Min Act: -0.0000

Data Index: 973772 (The Pile)

Max Activating Token Index: 130

Text #2

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.8546. Min Act: -0.0000

Data Index: 329294 (The Pile)

Max Activating Token Index: 40

Text #3

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7708. Min Act: -0.0000

Data Index: 1812213 (The Pile)

Max Activating Token Index: 870

Text #4

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.8171. Min Act: -0.0000

Data Index: 1212853 (The Pile)

Max Activating Token Index: 323

Text #5

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7927. Min Act: -0.0000

Data Index: 698261 (The Pile)

Max Activating Token Index: 103

Text #6

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7791. Min Act: -0.0000

Data Index: 1923308 (The Pile)

Max Activating Token Index: 663

Text #7

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.8028. Min Act: -0.0000

Data Index: 89022 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7615. Min Act: -0.0000

Data Index: 1937540 (The Pile)

Max Activating Token Index: 123

Text #9

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1332669 (The Pile)

Max Activating Token Index: 430

Text #10

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7079. Min Act: -0.0000

Data Index: 792110 (The Pile)

Max Activating Token Index: 39

Text #11

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7059. Min Act: -0.0000

Data Index: 132116 (The Pile)

Max Activating Token Index: 252

Text #12

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7283. Min Act: -0.0000

Data Index: 1171495 (The Pile)

Max Activating Token Index: 206

Text #13

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7768. Min Act: -0.0000

Data Index: 1000320 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6888. Min Act: -0.0000

Data Index: 1446413 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6520. Min Act: -0.0000

Data Index: 658504 (The Pile)

Max Activating Token Index: 721

Text #16

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6629. Min Act: -0.0000

Data Index: 697823 (The Pile)

Max Activating Token Index: 544

Text #17

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6744. Min Act: -0.0000

Data Index: 690375 (The Pile)

Max Activating Token Index: 861

Text #18

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.7026. Min Act: -0.0000

Data Index: 1181437 (The Pile)

Max Activating Token Index: 113

Text #19

Max Range: 1.0130. Min Range: -1.0130

Max Act: 0.6499. Min Act: -0.0000

Data Index: 843048 (The Pile)

Max Activating Token Index: 918