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

Dataset: The Pile

Neuron 1074 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.7425. Min Act: -0.0000

Data Index: 1611748 (The Pile)

Max Activating Token Index: 597

Text #1

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6738. Min Act: 0.0000

Data Index: 1685339 (The Pile)

Max Activating Token Index: 416

Text #2

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6055. Min Act: -0.0000

Data Index: 856493 (The Pile)

Max Activating Token Index: 328

Text #3

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6195. Min Act: 0.0000

Data Index: 1572868 (The Pile)

Max Activating Token Index: 121

Text #4

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.6301. Min Act: -0.0000

Data Index: 105542 (The Pile)

Max Activating Token Index: 25

Text #5

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5609. Min Act: -0.0000

Data Index: 76353 (The Pile)

Max Activating Token Index: 672

Text #6

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5715. Min Act: -0.0000

Data Index: 1576275 (The Pile)

Max Activating Token Index: 283

Text #7

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5277. Min Act: -0.0000

Data Index: 1285118 (The Pile)

Max Activating Token Index: 881

Text #8

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5707. Min Act: 0.0000

Data Index: 604047 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5170. Min Act: -0.0000

Data Index: 901493 (The Pile)

Max Activating Token Index: 224

Text #10

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5113. Min Act: -0.0000

Data Index: 809512 (The Pile)

Max Activating Token Index: 358

Text #11

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4836. Min Act: -0.0000

Data Index: 1762257 (The Pile)

Max Activating Token Index: 514

Text #12

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4997. Min Act: -0.0000

Data Index: 735762 (The Pile)

Max Activating Token Index: 77

Text #13

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5012. Min Act: -0.0000

Data Index: 1700032 (The Pile)

Max Activating Token Index: 419

Text #14

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4713. Min Act: -0.0000

Data Index: 1702827 (The Pile)

Max Activating Token Index: 746

Text #15

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.5149. Min Act: -0.0000

Data Index: 139493 (The Pile)

Max Activating Token Index: 638

Text #16

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1924925 (The Pile)

Max Activating Token Index: 855

Text #17

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4364. Min Act: -0.0000

Data Index: 575352 (The Pile)

Max Activating Token Index: 710

Text #18

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4596. Min Act: -0.0000

Data Index: 1289303 (The Pile)

Max Activating Token Index: 748

Text #19

Max Range: 0.7425. Min Range: -0.7425

Max Act: 0.4413. Min Act: -0.0000

Data Index: 28129 (The Pile)

Max Activating Token Index: 113