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

Dataset: The Pile

Neuron 3703 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: 0.5772. Min Range: -0.5772

Max Act: 0.5772. Min Act: -0.0000

Data Index: 483572 (The Pile)

Max Activating Token Index: 11

Text #1

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4079. Min Act: -0.0000

Data Index: 183021 (The Pile)

Max Activating Token Index: 1009

Text #2

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4139. Min Act: -0.0000

Data Index: 657227 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3693. Min Act: -0.0000

Data Index: 317517 (The Pile)

Max Activating Token Index: 478

Text #4

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.4208. Min Act: -0.0000

Data Index: 1732229 (The Pile)

Max Activating Token Index: 696

Text #5

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3925. Min Act: -0.0000

Data Index: 693000 (The Pile)

Max Activating Token Index: 732

Text #6

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3634. Min Act: 0.0000

Data Index: 213540 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3870. Min Act: -0.0000

Data Index: 1230784 (The Pile)

Max Activating Token Index: 640

Text #8

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3534. Min Act: -0.0000

Data Index: 492424 (The Pile)

Max Activating Token Index: 103

Text #9

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3382. Min Act: -0.0000

Data Index: 670362 (The Pile)

Max Activating Token Index: 168

Text #10

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3333. Min Act: 0.0000

Data Index: 1080064 (The Pile)

Max Activating Token Index: 461

Text #11

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3812. Min Act: -0.0000

Data Index: 1007779 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3646. Min Act: -0.0000

Data Index: 1378985 (The Pile)

Max Activating Token Index: 899

Text #13

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3500. Min Act: -0.0000

Data Index: 459189 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3397. Min Act: -0.0000

Data Index: 963621 (The Pile)

Max Activating Token Index: 925

Text #15

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3178. Min Act: -0.0000

Data Index: 1807180 (The Pile)

Max Activating Token Index: 240

Text #16

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3494. Min Act: -0.0000

Data Index: 359908 (The Pile)

Max Activating Token Index: 707

Text #17

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.2808. Min Act: -0.0000

Data Index: 252850 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3458. Min Act: -0.0000

Data Index: 1152515 (The Pile)

Max Activating Token Index: 749

Text #19

Max Range: 0.5772. Min Range: -0.5772

Max Act: 0.3423. Min Act: -0.0000

Data Index: 723978 (The Pile)

Max Activating Token Index: 528