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

Dataset: The Pile

Neuron 1061 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.5647. Min Act: -0.0000

Data Index: 571632 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.5596. Min Act: -0.0000

Data Index: 903817 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.5045. Min Act: -0.0000

Data Index: 1210708 (The Pile)

Max Activating Token Index: 824

Text #3

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.4421. Min Act: -0.0000

Data Index: 40921 (The Pile)

Max Activating Token Index: 467

Text #4

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.4112. Min Act: -0.0000

Data Index: 1236575 (The Pile)

Max Activating Token Index: 586

Text #5

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3602. Min Act: -0.0000

Data Index: 493106 (The Pile)

Max Activating Token Index: 916

Text #6

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3828. Min Act: -0.0000

Data Index: 1484966 (The Pile)

Max Activating Token Index: 639

Text #7

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3807. Min Act: -0.0000

Data Index: 1431925 (The Pile)

Max Activating Token Index: 893

Text #8

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3324. Min Act: -0.0000

Data Index: 105020 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3313. Min Act: -0.0000

Data Index: 1289435 (The Pile)

Max Activating Token Index: 721

Text #10

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.4018. Min Act: -0.0000

Data Index: 510488 (The Pile)

Max Activating Token Index: 1002

Text #11

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3041. Min Act: -0.0000

Data Index: 1135976 (The Pile)

Max Activating Token Index: 603

Text #12

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3409. Min Act: -0.0000

Data Index: 1943619 (The Pile)

Max Activating Token Index: 735

Text #13

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3313. Min Act: -0.0000

Data Index: 237026 (The Pile)

Max Activating Token Index: 1003

Text #14

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.2983. Min Act: -0.0000

Data Index: 114388 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1614983 (The Pile)

Max Activating Token Index: 790

Text #16

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.2429. Min Act: -0.0000

Data Index: 565625 (The Pile)

Max Activating Token Index: 490

Text #17

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3519. Min Act: -0.0000

Data Index: 43699 (The Pile)

Max Activating Token Index: 550

Text #18

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.3670. Min Act: -0.0000

Data Index: 778521 (The Pile)

Max Activating Token Index: 732

Text #19

Max Range: 1.5647. Min Range: -1.5647

Max Act: 1.2183. Min Act: -0.0000

Data Index: 529747 (The Pile)

Max Activating Token Index: 966