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

Dataset: The Pile

Neuron 4995 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: 4.1200. Min Range: -4.1200

Max Act: 3.8654. Min Act: -0.0000

Data Index: 803246 (The Pile)

Max Activating Token Index: 462

Text #1

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.8254. Min Act: -0.0000

Data Index: 1164170 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 4.1200. Min Range: -4.1200

Max Act: 4.1200. Min Act: -0.0000

Data Index: 653736 (The Pile)

Max Activating Token Index: 82

Text #3

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.5696. Min Act: -0.0000

Data Index: 478125 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.7541. Min Act: -0.0000

Data Index: 959084 (The Pile)

Max Activating Token Index: 643

Text #5

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.7432. Min Act: -0.0000

Data Index: 816665 (The Pile)

Max Activating Token Index: 827

Text #6

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.4229. Min Act: -0.0000

Data Index: 477194 (The Pile)

Max Activating Token Index: 649

Text #7

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.5102. Min Act: -0.0000

Data Index: 882785 (The Pile)

Max Activating Token Index: 606

Text #8

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.5118. Min Act: -0.0000

Data Index: 245343 (The Pile)

Max Activating Token Index: 547

Text #9

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.6622. Min Act: -0.0000

Data Index: 1253220 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.4088. Min Act: -0.0000

Data Index: 1774223 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.3941. Min Act: -0.0000

Data Index: 1517997 (The Pile)

Max Activating Token Index: 402

Text #12

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.5411. Min Act: -0.0000

Data Index: 1625523 (The Pile)

Max Activating Token Index: 36

Text #13

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.0319. Min Act: -0.0000

Data Index: 179374 (The Pile)

Max Activating Token Index: 492

Text #14

Max Range: 4.1200. Min Range: -4.1200

Max Act: 2.7144. Min Act: -0.0000

Data Index: 1669732 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.1542. Min Act: -0.0000

Data Index: 1850506 (The Pile)

Max Activating Token Index: 185

Text #16

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.2205. Min Act: -0.0000

Data Index: 1568552 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.0765. Min Act: -0.0000

Data Index: 361222 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.0798. Min Act: -0.0000

Data Index: 1973214 (The Pile)

Max Activating Token Index: 469

Text #19

Max Range: 4.1200. Min Range: -4.1200

Max Act: 3.0398. Min Act: -0.0000

Data Index: 1408280 (The Pile)

Max Activating Token Index: 63