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

Dataset: The Pile

Neuron 1254 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6626. Min Act: -0.0000

Data Index: 637841 (The Pile)

Max Activating Token Index: 962

Text #1

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1848271 (The Pile)

Max Activating Token Index: 379

Text #2

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6276. Min Act: -0.0000

Data Index: 834902 (The Pile)

Max Activating Token Index: 807

Text #3

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.6732. Min Act: -0.0000

Data Index: 1833128 (The Pile)

Max Activating Token Index: 1004

Text #4

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5680. Min Act: -0.0000

Data Index: 498483 (The Pile)

Max Activating Token Index: 965

Text #5

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5579. Min Act: -0.0000

Data Index: 1308925 (The Pile)

Max Activating Token Index: 1006

Text #6

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5541. Min Act: -0.0000

Data Index: 398695 (The Pile)

Max Activating Token Index: 974

Text #7

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5667. Min Act: -0.0000

Data Index: 172270 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1681777 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5288. Min Act: -0.0000

Data Index: 591369 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1321149 (The Pile)

Max Activating Token Index: 333

Text #11

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5366. Min Act: -0.0000

Data Index: 902928 (The Pile)

Max Activating Token Index: 1015

Text #12

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5209. Min Act: -0.0000

Data Index: 965543 (The Pile)

Max Activating Token Index: 981

Text #13

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4541. Min Act: -0.0000

Data Index: 1368662 (The Pile)

Max Activating Token Index: 798

Text #14

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1407278 (The Pile)

Max Activating Token Index: 984

Text #15

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5031. Min Act: -0.0000

Data Index: 1525957 (The Pile)

Max Activating Token Index: 929

Text #16

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5336. Min Act: -0.0000

Data Index: 1158102 (The Pile)

Max Activating Token Index: 585

Text #17

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5605. Min Act: -0.0000

Data Index: 950014 (The Pile)

Max Activating Token Index: 795

Text #18

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.4830. Min Act: -0.0000

Data Index: 129077 (The Pile)

Max Activating Token Index: 500

Text #19

Max Range: 0.6732. Min Range: -0.6732

Max Act: 0.5005. Min Act: -0.0000

Data Index: 1165116 (The Pile)

Max Activating Token Index: 878