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

Dataset: The Pile

Neuron 3679 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: 0.2664. Min Range: -0.2664

Max Act: 0.2664. Min Act: -0.0000

Data Index: 299906 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2258. Min Act: -0.0000

Data Index: 811248 (The Pile)

Max Activating Token Index: 911

Text #2

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2523. Min Act: -0.0000

Data Index: 717254 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2167. Min Act: -0.0000

Data Index: 946939 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1074354 (The Pile)

Max Activating Token Index: 940

Text #5

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2112. Min Act: -0.0000

Data Index: 658642 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2121. Min Act: -0.0000

Data Index: 328724 (The Pile)

Max Activating Token Index: 130

Text #7

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2060. Min Act: -0.0000

Data Index: 352157 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2113. Min Act: -0.0000

Data Index: 1238217 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1851469 (The Pile)

Max Activating Token Index: 154

Text #10

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1972. Min Act: -0.0000

Data Index: 756188 (The Pile)

Max Activating Token Index: 362

Text #11

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1818. Min Act: -0.0000

Data Index: 313729 (The Pile)

Max Activating Token Index: 165

Text #12

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1990. Min Act: -0.0000

Data Index: 69540 (The Pile)

Max Activating Token Index: 159

Text #13

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1897. Min Act: -0.0000

Data Index: 260601 (The Pile)

Max Activating Token Index: 493

Text #14

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1826. Min Act: -0.0000

Data Index: 306252 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1856. Min Act: -0.0000

Data Index: 1346715 (The Pile)

Max Activating Token Index: 657

Text #16

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1842. Min Act: -0.0000

Data Index: 1318394 (The Pile)

Max Activating Token Index: 939

Text #17

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1457253 (The Pile)

Max Activating Token Index: 363

Text #18

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1891. Min Act: -0.0000

Data Index: 1201260 (The Pile)

Max Activating Token Index: 916

Text #19

Max Range: 0.2664. Min Range: -0.2664

Max Act: 0.1743. Min Act: -0.0000

Data Index: 795056 (The Pile)

Max Activating Token Index: 640