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

Dataset: The Pile

Neuron 493 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: 0.4823. Min Range: -0.4823

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1429949 (The Pile)

Max Activating Token Index: 730

Text #1

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4243. Min Act: -0.0000

Data Index: 739926 (The Pile)

Max Activating Token Index: 286

Text #2

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4054. Min Act: -0.0000

Data Index: 1202962 (The Pile)

Max Activating Token Index: 54

Text #3

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4312. Min Act: 0.0001

Data Index: 1833442 (The Pile)

Max Activating Token Index: 691

Text #4

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3948. Min Act: -0.0000

Data Index: 26012 (The Pile)

Max Activating Token Index: 858

Text #5

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3606. Min Act: -0.0000

Data Index: 379493 (The Pile)

Max Activating Token Index: 969

Text #6

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3909. Min Act: -0.0000

Data Index: 172530 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3627. Min Act: -0.0000

Data Index: 1625344 (The Pile)

Max Activating Token Index: 515

Text #8

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.4181. Min Act: -0.0000

Data Index: 1330856 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3677. Min Act: -0.0000

Data Index: 1043242 (The Pile)

Max Activating Token Index: 940

Text #10

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3480. Min Act: -0.0000

Data Index: 1929690 (The Pile)

Max Activating Token Index: 689

Text #11

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3479. Min Act: -0.0000

Data Index: 1909332 (The Pile)

Max Activating Token Index: 474

Text #12

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3575. Min Act: -0.0000

Data Index: 36411 (The Pile)

Max Activating Token Index: 870

Text #13

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3436. Min Act: -0.0000

Data Index: 37211 (The Pile)

Max Activating Token Index: 564

Text #14

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3390. Min Act: -0.0000

Data Index: 657861 (The Pile)

Max Activating Token Index: 297

Text #15

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3260. Min Act: -0.0000

Data Index: 1419594 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3329. Min Act: -0.0000

Data Index: 1121664 (The Pile)

Max Activating Token Index: 835

Text #17

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3435. Min Act: -0.0000

Data Index: 1051007 (The Pile)

Max Activating Token Index: 416

Text #18

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3299. Min Act: -0.0000

Data Index: 1875529 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 0.4823. Min Range: -0.4823

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1448451 (The Pile)

Max Activating Token Index: 463