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

Dataset: The Pile

Neuron 3462 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: 3.5911. Min Range: -3.5911

Max Act: 3.5911. Min Act: -0.0000

Data Index: 1802793 (The Pile)

Max Activating Token Index: 174

Text #1

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.4024. Min Act: -0.0000

Data Index: 1230983 (The Pile)

Max Activating Token Index: 14

Text #2

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.1750. Min Act: -0.0000

Data Index: 721519 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.2434. Min Act: -0.0000

Data Index: 1365519 (The Pile)

Max Activating Token Index: 939

Text #4

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.2157. Min Act: -0.0000

Data Index: 1763358 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.1787. Min Act: -0.0000

Data Index: 32641 (The Pile)

Max Activating Token Index: 385

Text #6

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.0520. Min Act: -0.0000

Data Index: 116534 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1383180 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.1904. Min Act: -0.0000

Data Index: 702008 (The Pile)

Max Activating Token Index: 518

Text #9

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9713. Min Act: -0.0000

Data Index: 443977 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9610. Min Act: -0.0000

Data Index: 623705 (The Pile)

Max Activating Token Index: 544

Text #11

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9968. Min Act: -0.0000

Data Index: 740124 (The Pile)

Max Activating Token Index: 714

Text #12

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1957647 (The Pile)

Max Activating Token Index: 172

Text #13

Max Range: 3.5911. Min Range: -3.5911

Max Act: 1.0704. Min Act: -0.0000

Data Index: 950577 (The Pile)

Max Activating Token Index: 535

Text #14

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1208699 (The Pile)

Max Activating Token Index: 125

Text #15

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1918532 (The Pile)

Max Activating Token Index: 780

Text #16

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9401. Min Act: -0.0000

Data Index: 843220 (The Pile)

Max Activating Token Index: 651

Text #17

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9552. Min Act: -0.0000

Data Index: 1241583 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.8808. Min Act: -0.0000

Data Index: 368069 (The Pile)

Max Activating Token Index: 826

Text #19

Max Range: 3.5911. Min Range: -3.5911

Max Act: 0.9458. Min Act: -0.0000

Data Index: 506594 (The Pile)

Max Activating Token Index: 808