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

Dataset: The Pile

Neuron 2903 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0714. Min Act: -0.0000

Data Index: 299446 (The Pile)

Max Activating Token Index: 571

Text #1

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1263671 (The Pile)

Max Activating Token Index: 265

Text #2

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0062. Min Act: -0.0000

Data Index: 1890185 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 1.0714. Min Range: -1.0714

Max Act: 1.0004. Min Act: -0.0000

Data Index: 490406 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9667. Min Act: -0.0000

Data Index: 1145090 (The Pile)

Max Activating Token Index: 948

Text #5

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9670. Min Act: -0.0000

Data Index: 486025 (The Pile)

Max Activating Token Index: 647

Text #6

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9962. Min Act: -0.0000

Data Index: 155991 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9402. Min Act: -0.0000

Data Index: 1727073 (The Pile)

Max Activating Token Index: 332

Text #8

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1722532 (The Pile)

Max Activating Token Index: 228

Text #9

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9586. Min Act: -0.0000

Data Index: 1598937 (The Pile)

Max Activating Token Index: 812

Text #10

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9492. Min Act: -0.0000

Data Index: 294695 (The Pile)

Max Activating Token Index: 376

Text #11

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1058160 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9584. Min Act: -0.0000

Data Index: 1111749 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9151. Min Act: -0.0000

Data Index: 711626 (The Pile)

Max Activating Token Index: 908

Text #14

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9163. Min Act: -0.0000

Data Index: 482327 (The Pile)

Max Activating Token Index: 345

Text #15

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8896. Min Act: -0.0000

Data Index: 131958 (The Pile)

Max Activating Token Index: 730

Text #16

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9007. Min Act: -0.0000

Data Index: 1574650 (The Pile)

Max Activating Token Index: 299

Text #17

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.9306. Min Act: -0.0000

Data Index: 754412 (The Pile)

Max Activating Token Index: 765

Text #18

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8725. Min Act: -0.0000

Data Index: 1741159 (The Pile)

Max Activating Token Index: 289

Text #19

Max Range: 1.0714. Min Range: -1.0714

Max Act: 0.8957. Min Act: -0.0000

Data Index: 639810 (The Pile)

Max Activating Token Index: 229