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

Dataset: The Pile

Neuron 3514 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: 1.1628. Min Range: -1.1628

Max Act: 1.1628. Min Act: -0.0000

Data Index: 1738450 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0352. Min Act: -0.0000

Data Index: 900212 (The Pile)

Max Activating Token Index: 712

Text #2

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0189. Min Act: -0.0000

Data Index: 254158 (The Pile)

Max Activating Token Index: 899

Text #3

Max Range: 1.1628. Min Range: -1.1628

Max Act: 1.0474. Min Act: -0.0000

Data Index: 1067390 (The Pile)

Max Activating Token Index: 344

Text #4

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9136. Min Act: -0.0000

Data Index: 1720032 (The Pile)

Max Activating Token Index: 279

Text #5

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8686. Min Act: -0.0000

Data Index: 934576 (The Pile)

Max Activating Token Index: 966

Text #6

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8743. Min Act: -0.0000

Data Index: 19111 (The Pile)

Max Activating Token Index: 771

Text #7

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8064. Min Act: -0.0000

Data Index: 1871617 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1805300 (The Pile)

Max Activating Token Index: 708

Text #9

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8158. Min Act: -0.0000

Data Index: 1725699 (The Pile)

Max Activating Token Index: 564

Text #10

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6502. Min Act: -0.0000

Data Index: 38475 (The Pile)

Max Activating Token Index: 207

Text #11

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.8445. Min Act: -0.0000

Data Index: 757302 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6247. Min Act: -0.0000

Data Index: 172627 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.7176. Min Act: -0.0000

Data Index: 349058 (The Pile)

Max Activating Token Index: 245

Text #14

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6822. Min Act: -0.0000

Data Index: 1118012 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6172. Min Act: -0.0000

Data Index: 1962097 (The Pile)

Max Activating Token Index: 534

Text #16

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.6680. Min Act: -0.0000

Data Index: 255329 (The Pile)

Max Activating Token Index: 557

Text #17

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.5783. Min Act: -0.0000

Data Index: 98758 (The Pile)

Max Activating Token Index: 235

Text #18

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.5725. Min Act: -0.0000

Data Index: 639195 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.1628. Min Range: -1.1628

Max Act: 0.5897. Min Act: -0.0000

Data Index: 791137 (The Pile)

Max Activating Token Index: 841