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

Dataset: The Pile

Neuron 3866 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.8084. Min Act: -0.0000

Data Index: 1965105 (The Pile)

Max Activating Token Index: 394

Text #1

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4773. Min Act: -0.0000

Data Index: 378862 (The Pile)

Max Activating Token Index: 749

Text #2

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.6007. Min Act: -0.0000

Data Index: 744125 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.5814. Min Act: -0.0000

Data Index: 416257 (The Pile)

Max Activating Token Index: 687

Text #4

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4019. Min Act: -0.0000

Data Index: 1355114 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4930. Min Act: -0.0000

Data Index: 1744542 (The Pile)

Max Activating Token Index: 743

Text #6

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.4601. Min Act: -0.0000

Data Index: 1747829 (The Pile)

Max Activating Token Index: 1005

Text #7

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3663. Min Act: -0.0000

Data Index: 511442 (The Pile)

Max Activating Token Index: 943

Text #8

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1186314 (The Pile)

Max Activating Token Index: 690

Text #9

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.5356. Min Act: -0.0000

Data Index: 1535902 (The Pile)

Max Activating Token Index: 591

Text #10

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3931. Min Act: -0.0000

Data Index: 979989 (The Pile)

Max Activating Token Index: 640

Text #11

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3987. Min Act: -0.0000

Data Index: 1404524 (The Pile)

Max Activating Token Index: 670

Text #12

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3107. Min Act: -0.0000

Data Index: 1681365 (The Pile)

Max Activating Token Index: 641

Text #13

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1707247 (The Pile)

Max Activating Token Index: 666

Text #14

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3056. Min Act: -0.0000

Data Index: 1739459 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3007. Min Act: -0.0000

Data Index: 1300676 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3866. Min Act: -0.0000

Data Index: 444295 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3754. Min Act: -0.0000

Data Index: 936458 (The Pile)

Max Activating Token Index: 316

Text #18

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3787. Min Act: -0.0000

Data Index: 1202782 (The Pile)

Max Activating Token Index: 1015

Text #19

Max Range: 1.8084. Min Range: -1.8084

Max Act: 1.3098. Min Act: -0.0000

Data Index: 181499 (The Pile)

Max Activating Token Index: 169