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

Dataset: The Pile

Neuron 3733 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: 1.5251. Min Range: -1.5251

Max Act: 1.4719. Min Act: -0.0000

Data Index: 1240634 (The Pile)

Max Activating Token Index: 345

Text #1

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3652. Min Act: -0.0000

Data Index: 1915123 (The Pile)

Max Activating Token Index: 172

Text #2

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1089561 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3086. Min Act: -0.0000

Data Index: 958154 (The Pile)

Max Activating Token Index: 723

Text #4

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.2843. Min Act: -0.0000

Data Index: 999317 (The Pile)

Max Activating Token Index: 460

Text #5

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.5251. Min Act: -0.0000

Data Index: 226897 (The Pile)

Max Activating Token Index: 784

Text #6

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3444. Min Act: -0.0000

Data Index: 963563 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1995. Min Act: -0.0000

Data Index: 794940 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.3356. Min Act: -0.0000

Data Index: 1165748 (The Pile)

Max Activating Token Index: 995

Text #9

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1674. Min Act: -0.0000

Data Index: 1856461 (The Pile)

Max Activating Token Index: 970

Text #10

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1445. Min Act: -0.0000

Data Index: 1862889 (The Pile)

Max Activating Token Index: 125

Text #11

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.0718. Min Act: -0.0000

Data Index: 848415 (The Pile)

Max Activating Token Index: 799

Text #12

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1479. Min Act: -0.0000

Data Index: 117793 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.2091. Min Act: -0.0000

Data Index: 558335 (The Pile)

Max Activating Token Index: 33

Text #14

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1933. Min Act: -0.0000

Data Index: 1519980 (The Pile)

Max Activating Token Index: 295

Text #15

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1323. Min Act: -0.0000

Data Index: 1078634 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1070. Min Act: -0.0000

Data Index: 158592 (The Pile)

Max Activating Token Index: 136

Text #17

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1731. Min Act: -0.0000

Data Index: 395961 (The Pile)

Max Activating Token Index: 25

Text #18

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1192616 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 1.5251. Min Range: -1.5251

Max Act: 1.0789. Min Act: -0.0000

Data Index: 1667753 (The Pile)

Max Activating Token Index: 853