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

Dataset: The Pile

Neuron 2285 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: 1.3929. Min Range: -1.3929

Max Act: 1.3929. Min Act: -0.0000

Data Index: 381298 (The Pile)

Max Activating Token Index: 271

Text #1

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.3851. Min Act: -0.0000

Data Index: 1892173 (The Pile)

Max Activating Token Index: 80

Text #2

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.3303. Min Act: -0.0000

Data Index: 1522682 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.2494. Min Act: -0.0000

Data Index: 1728424 (The Pile)

Max Activating Token Index: 50

Text #4

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.1441. Min Act: -0.0000

Data Index: 1661055 (The Pile)

Max Activating Token Index: 141

Text #5

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.2912. Min Act: -0.0000

Data Index: 1861821 (The Pile)

Max Activating Token Index: 870

Text #6

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.1186. Min Act: -0.0000

Data Index: 1400770 (The Pile)

Max Activating Token Index: 358

Text #7

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.1576. Min Act: -0.0000

Data Index: 1718722 (The Pile)

Max Activating Token Index: 173

Text #8

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.0539. Min Act: -0.0000

Data Index: 622757 (The Pile)

Max Activating Token Index: 681

Text #9

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.0757. Min Act: -0.0000

Data Index: 1102025 (The Pile)

Max Activating Token Index: 918

Text #10

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.1987. Min Act: -0.0000

Data Index: 1991207 (The Pile)

Max Activating Token Index: 242

Text #11

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.1006. Min Act: -0.0000

Data Index: 1060751 (The Pile)

Max Activating Token Index: 625

Text #12

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.0606. Min Act: -0.0000

Data Index: 862329 (The Pile)

Max Activating Token Index: 1016

Text #13

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.0873. Min Act: -0.0000

Data Index: 1982412 (The Pile)

Max Activating Token Index: 462

Text #14

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.0319. Min Act: -0.0000

Data Index: 850464 (The Pile)

Max Activating Token Index: 421

Text #15

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.1189. Min Act: -0.0000

Data Index: 1191987 (The Pile)

Max Activating Token Index: 932

Text #16

Max Range: 1.3929. Min Range: -1.3929

Max Act: 0.9369. Min Act: -0.0000

Data Index: 602596 (The Pile)

Max Activating Token Index: 734

Text #17

Max Range: 1.3929. Min Range: -1.3929

Max Act: 0.9674. Min Act: -0.0000

Data Index: 503468 (The Pile)

Max Activating Token Index: 1004

Text #18

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.0404. Min Act: -0.0000

Data Index: 595135 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 1.3929. Min Range: -1.3929

Max Act: 1.0681. Min Act: -0.0000

Data Index: 1113447 (The Pile)

Max Activating Token Index: 151