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

Dataset: The Pile

Neuron 4039 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.2745. Min Act: -0.0000

Data Index: 1967702 (The Pile)

Max Activating Token Index: 1006

Text #1

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0691. Min Act: -0.0000

Data Index: 38380 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0342. Min Act: -0.0000

Data Index: 879588 (The Pile)

Max Activating Token Index: 516

Text #3

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.1930. Min Act: -0.0000

Data Index: 1405179 (The Pile)

Max Activating Token Index: 821

Text #4

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0714. Min Act: -0.0000

Data Index: 1579672 (The Pile)

Max Activating Token Index: 648

Text #5

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0867. Min Act: -0.0000

Data Index: 1045523 (The Pile)

Max Activating Token Index: 503

Text #6

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9680. Min Act: -0.0000

Data Index: 684185 (The Pile)

Max Activating Token Index: 586

Text #7

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0344. Min Act: -0.0000

Data Index: 569707 (The Pile)

Max Activating Token Index: 957

Text #8

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9254. Min Act: -0.0000

Data Index: 777329 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0395. Min Act: -0.0000

Data Index: 1645343 (The Pile)

Max Activating Token Index: 871

Text #10

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1548486 (The Pile)

Max Activating Token Index: 720

Text #11

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.8850. Min Act: -0.0000

Data Index: 934391 (The Pile)

Max Activating Token Index: 341

Text #12

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0884. Min Act: -0.0000

Data Index: 172708 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9493. Min Act: -0.0000

Data Index: 1438722 (The Pile)

Max Activating Token Index: 128

Text #14

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9816. Min Act: -0.0000

Data Index: 352183 (The Pile)

Max Activating Token Index: 980

Text #15

Max Range: 1.2745. Min Range: -1.2745

Max Act: 1.0245. Min Act: -0.0000

Data Index: 549313 (The Pile)

Max Activating Token Index: 991

Text #16

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1946677 (The Pile)

Max Activating Token Index: 808

Text #17

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.8899. Min Act: -0.0000

Data Index: 1045535 (The Pile)

Max Activating Token Index: 437

Text #18

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9465. Min Act: -0.0000

Data Index: 552778 (The Pile)

Max Activating Token Index: 711

Text #19

Max Range: 1.2745. Min Range: -1.2745

Max Act: 0.9617. Min Act: -0.0000

Data Index: 689245 (The Pile)

Max Activating Token Index: 961