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

Dataset: The Pile

Neuron 1018 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: 0.4453. Min Range: -0.4453

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1474307 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1736039 (The Pile)

Max Activating Token Index: 583

Text #2

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3864. Min Act: -0.0000

Data Index: 1818242 (The Pile)

Max Activating Token Index: 968

Text #3

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3589. Min Act: -0.0000

Data Index: 299489 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3419. Min Act: -0.0000

Data Index: 517748 (The Pile)

Max Activating Token Index: 254

Text #5

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3284. Min Act: -0.0000

Data Index: 1233199 (The Pile)

Max Activating Token Index: 913

Text #6

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3383. Min Act: -0.0000

Data Index: 1678978 (The Pile)

Max Activating Token Index: 156

Text #7

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3253. Min Act: -0.0000

Data Index: 1840798 (The Pile)

Max Activating Token Index: 552

Text #8

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3376. Min Act: -0.0000

Data Index: 1890111 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3312. Min Act: -0.0000

Data Index: 985312 (The Pile)

Max Activating Token Index: 146

Text #10

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3665. Min Act: -0.0000

Data Index: 1714049 (The Pile)

Max Activating Token Index: 742

Text #11

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3040. Min Act: -0.0000

Data Index: 1609416 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3257. Min Act: -0.0000

Data Index: 584189 (The Pile)

Max Activating Token Index: 382

Text #13

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3332. Min Act: -0.0000

Data Index: 109849 (The Pile)

Max Activating Token Index: 42

Text #14

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3074. Min Act: -0.0000

Data Index: 890373 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3185. Min Act: -0.0000

Data Index: 584474 (The Pile)

Max Activating Token Index: 515

Text #16

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3109. Min Act: -0.0000

Data Index: 662718 (The Pile)

Max Activating Token Index: 682

Text #17

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.3290. Min Act: -0.0000

Data Index: 954039 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.2922. Min Act: -0.0000

Data Index: 514885 (The Pile)

Max Activating Token Index: 616

Text #19

Max Range: 0.4453. Min Range: -0.4453

Max Act: 0.2918. Min Act: -0.0000

Data Index: 574133 (The Pile)

Max Activating Token Index: 207