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

Dataset: The Pile

Neuron 364 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4714. Min Act: -0.0000

Data Index: 1453329 (The Pile)

Max Activating Token Index: 845

Text #1

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4054. Min Act: -0.0000

Data Index: 271912 (The Pile)

Max Activating Token Index: 31

Text #2

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1657559 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.4236. Min Act: -0.0000

Data Index: 1055687 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3523. Min Act: -0.0000

Data Index: 259963 (The Pile)

Max Activating Token Index: 1013

Text #5

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3537. Min Act: -0.0000

Data Index: 1394144 (The Pile)

Max Activating Token Index: 974

Text #6

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3785. Min Act: -0.0000

Data Index: 184424 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3662. Min Act: 0.0000

Data Index: 955167 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3269. Min Act: -0.0000

Data Index: 1229918 (The Pile)

Max Activating Token Index: 920

Text #9

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3467. Min Act: -0.0000

Data Index: 1097994 (The Pile)

Max Activating Token Index: 11

Text #10

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3412. Min Act: -0.0000

Data Index: 252949 (The Pile)

Max Activating Token Index: 644

Text #11

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1143870 (The Pile)

Max Activating Token Index: 619

Text #12

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3322. Min Act: -0.0000

Data Index: 697359 (The Pile)

Max Activating Token Index: 31

Text #13

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1828326 (The Pile)

Max Activating Token Index: 824

Text #14

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3475. Min Act: -0.0000

Data Index: 1134551 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3466. Min Act: -0.0000

Data Index: 68304 (The Pile)

Max Activating Token Index: 933

Text #16

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3248. Min Act: 0.0000

Data Index: 517381 (The Pile)

Max Activating Token Index: 92

Text #17

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3325. Min Act: -0.0000

Data Index: 1571414 (The Pile)

Max Activating Token Index: 539

Text #18

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3363. Min Act: -0.0000

Data Index: 455240 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.4714. Min Range: -0.4714

Max Act: 0.3466. Min Act: -0.0000

Data Index: 1465423 (The Pile)

Max Activating Token Index: 183