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

Dataset: The Pile

Neuron 3320 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: 0.4508. Min Range: -0.4508

Max Act: 0.4508. Min Act: -0.0000

Data Index: 869720 (The Pile)

Max Activating Token Index: 244

Text #1

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.4455. Min Act: -0.0000

Data Index: 936895 (The Pile)

Max Activating Token Index: 64

Text #2

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3823. Min Act: -0.0000

Data Index: 27260 (The Pile)

Max Activating Token Index: 584

Text #3

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3697. Min Act: -0.0000

Data Index: 1527325 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3690. Min Act: -0.0000

Data Index: 309534 (The Pile)

Max Activating Token Index: 191

Text #5

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3680. Min Act: -0.0000

Data Index: 1329373 (The Pile)

Max Activating Token Index: 151

Text #6

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3434. Min Act: -0.0000

Data Index: 1638232 (The Pile)

Max Activating Token Index: 377

Text #7

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3343. Min Act: -0.0000

Data Index: 869403 (The Pile)

Max Activating Token Index: 785

Text #8

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3258. Min Act: -0.0000

Data Index: 1833805 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3103. Min Act: -0.0000

Data Index: 1897152 (The Pile)

Max Activating Token Index: 345

Text #10

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3107. Min Act: -0.0000

Data Index: 1020487 (The Pile)

Max Activating Token Index: 315

Text #11

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3243. Min Act: -0.0000

Data Index: 1500992 (The Pile)

Max Activating Token Index: 821

Text #12

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.3074. Min Act: -0.0000

Data Index: 758248 (The Pile)

Max Activating Token Index: 379

Text #13

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2971. Min Act: -0.0000

Data Index: 267433 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2774. Min Act: -0.0000

Data Index: 895052 (The Pile)

Max Activating Token Index: 476

Text #15

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2850. Min Act: -0.0000

Data Index: 1996865 (The Pile)

Max Activating Token Index: 462

Text #16

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2810. Min Act: -0.0000

Data Index: 587500 (The Pile)

Max Activating Token Index: 154

Text #17

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2792. Min Act: -0.0000

Data Index: 232868 (The Pile)

Max Activating Token Index: 413

Text #18

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2838. Min Act: -0.0000

Data Index: 228121 (The Pile)

Max Activating Token Index: 136

Text #19

Max Range: 0.4508. Min Range: -0.4508

Max Act: 0.2741. Min Act: -0.0000

Data Index: 256413 (The Pile)

Max Activating Token Index: 527