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

Dataset: The Pile

Neuron 888 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.4558. Min Act: -0.0000

Data Index: 29431 (The Pile)

Max Activating Token Index: 711

Text #1

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3625. Min Act: -0.0000

Data Index: 147199 (The Pile)

Max Activating Token Index: 355

Text #2

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3728. Min Act: -0.0000

Data Index: 977702 (The Pile)

Max Activating Token Index: 519

Text #3

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3649. Min Act: -0.0000

Data Index: 191799 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3885. Min Act: -0.0000

Data Index: 50736 (The Pile)

Max Activating Token Index: 196

Text #5

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3795. Min Act: -0.0000

Data Index: 462294 (The Pile)

Max Activating Token Index: 516

Text #6

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3849. Min Act: -0.0000

Data Index: 1257352 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1230648 (The Pile)

Max Activating Token Index: 548

Text #8

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3154. Min Act: -0.0000

Data Index: 379424 (The Pile)

Max Activating Token Index: 483

Text #9

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3414. Min Act: -0.0000

Data Index: 1830360 (The Pile)

Max Activating Token Index: 192

Text #10

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3173. Min Act: -0.0000

Data Index: 1906050 (The Pile)

Max Activating Token Index: 457

Text #11

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3090. Min Act: -0.0000

Data Index: 356339 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.3209. Min Act: -0.0000

Data Index: 1398170 (The Pile)

Max Activating Token Index: 499

Text #13

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.2732. Min Act: -0.0000

Data Index: 1315704 (The Pile)

Max Activating Token Index: 812

Text #14

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.2920. Min Act: -0.0000

Data Index: 257721 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.2551. Min Act: -0.0000

Data Index: 1655466 (The Pile)

Max Activating Token Index: 309

Text #16

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.2800. Min Act: -0.0000

Data Index: 1795639 (The Pile)

Max Activating Token Index: 137

Text #17

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.2718. Min Act: -0.0000

Data Index: 359567 (The Pile)

Max Activating Token Index: 829

Text #18

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.2428. Min Act: -0.0000

Data Index: 926880 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.4558. Min Range: -0.4558

Max Act: 0.2285. Min Act: -0.0000

Data Index: 1022660 (The Pile)

Max Activating Token Index: 544