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

Dataset: The Pile

Neuron 4650 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: 0.4350. Min Range: -0.4350

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1270800 (The Pile)

Max Activating Token Index: 1022

Text #1

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1864778 (The Pile)

Max Activating Token Index: 987

Text #2

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3641. Min Act: -0.0000

Data Index: 968022 (The Pile)

Max Activating Token Index: 79

Text #3

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3723. Min Act: -0.0000

Data Index: 309571 (The Pile)

Max Activating Token Index: 38

Text #4

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3375. Min Act: -0.0000

Data Index: 1838541 (The Pile)

Max Activating Token Index: 794

Text #5

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3856. Min Act: -0.0000

Data Index: 10787 (The Pile)

Max Activating Token Index: 984

Text #6

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3698. Min Act: -0.0000

Data Index: 1817628 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3587. Min Act: -0.0000

Data Index: 954603 (The Pile)

Max Activating Token Index: 117

Text #8

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3539. Min Act: -0.0000

Data Index: 515612 (The Pile)

Max Activating Token Index: 946

Text #9

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3421. Min Act: -0.0000

Data Index: 56082 (The Pile)

Max Activating Token Index: 276

Text #10

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3439. Min Act: -0.0000

Data Index: 1292563 (The Pile)

Max Activating Token Index: 1020

Text #11

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3484. Min Act: -0.0000

Data Index: 100186 (The Pile)

Max Activating Token Index: 180

Text #12

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3426. Min Act: -0.0000

Data Index: 1945815 (The Pile)

Max Activating Token Index: 827

Text #13

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3347. Min Act: -0.0000

Data Index: 228232 (The Pile)

Max Activating Token Index: 127

Text #14

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3505. Min Act: -0.0000

Data Index: 1960650 (The Pile)

Max Activating Token Index: 110

Text #15

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3300. Min Act: -0.0000

Data Index: 1552952 (The Pile)

Max Activating Token Index: 520

Text #16

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3262. Min Act: -0.0000

Data Index: 750072 (The Pile)

Max Activating Token Index: 607

Text #17

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3147. Min Act: -0.0000

Data Index: 1968344 (The Pile)

Max Activating Token Index: 564

Text #18

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3405. Min Act: -0.0000

Data Index: 311984 (The Pile)

Max Activating Token Index: 78

Text #19

Max Range: 0.4350. Min Range: -0.4350

Max Act: 0.3627. Min Act: -0.0000

Data Index: 704999 (The Pile)

Max Activating Token Index: 806