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

Dataset: The Pile

Neuron 3970 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2766. Min Act: -0.0000

Data Index: 1507242 (The Pile)

Max Activating Token Index: 753

Text #1

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1223. Min Act: -0.0000

Data Index: 981932 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0951. Min Act: -0.0000

Data Index: 293676 (The Pile)

Max Activating Token Index: 772

Text #3

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0931. Min Act: -0.0000

Data Index: 73656 (The Pile)

Max Activating Token Index: 807

Text #4

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0841. Min Act: -0.0000

Data Index: 257143 (The Pile)

Max Activating Token Index: 190

Text #5

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1602296 (The Pile)

Max Activating Token Index: 426

Text #6

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2641. Min Act: -0.0000

Data Index: 1780270 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9631. Min Act: -0.0000

Data Index: 380562 (The Pile)

Max Activating Token Index: 510

Text #8

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0792. Min Act: -0.0000

Data Index: 1319863 (The Pile)

Max Activating Token Index: 175

Text #9

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1284. Min Act: -0.0000

Data Index: 1955663 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9713. Min Act: -0.0000

Data Index: 982126 (The Pile)

Max Activating Token Index: 865

Text #11

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.8905. Min Act: -0.0000

Data Index: 36416 (The Pile)

Max Activating Token Index: 336

Text #12

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1013712 (The Pile)

Max Activating Token Index: 632

Text #13

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0143. Min Act: -0.0000

Data Index: 450343 (The Pile)

Max Activating Token Index: 178

Text #14

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0079. Min Act: -0.0000

Data Index: 1972142 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.9850. Min Act: -0.0000

Data Index: 240548 (The Pile)

Max Activating Token Index: 313

Text #16

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0068. Min Act: -0.0000

Data Index: 381846 (The Pile)

Max Activating Token Index: 96

Text #17

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0326. Min Act: -0.0000

Data Index: 934813 (The Pile)

Max Activating Token Index: 169

Text #18

Max Range: 1.2766. Min Range: -1.2766

Max Act: 0.8116. Min Act: -0.0000

Data Index: 1075328 (The Pile)

Max Activating Token Index: 623

Text #19

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.0927. Min Act: -0.0000

Data Index: 1013424 (The Pile)

Max Activating Token Index: 722