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

Dataset: The Pile

Neuron 4918 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: 1.7856. Min Range: -1.7856

Max Act: 1.7856. Min Act: -0.0000

Data Index: 1729876 (The Pile)

Max Activating Token Index: 412

Text #1

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.6076. Min Act: -0.0000

Data Index: 1890218 (The Pile)

Max Activating Token Index: 52

Text #2

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.2723. Min Act: -0.0000

Data Index: 154911 (The Pile)

Max Activating Token Index: 862

Text #3

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.4338. Min Act: -0.0000

Data Index: 1861672 (The Pile)

Max Activating Token Index: 500

Text #4

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.1781. Min Act: -0.0000

Data Index: 587961 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0591. Min Act: -0.0000

Data Index: 309652 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.1712. Min Act: -0.0000

Data Index: 629156 (The Pile)

Max Activating Token Index: 159

Text #7

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0250. Min Act: -0.0000

Data Index: 1786163 (The Pile)

Max Activating Token Index: 917

Text #8

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0651. Min Act: -0.0000

Data Index: 1595251 (The Pile)

Max Activating Token Index: 656

Text #9

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1964650 (The Pile)

Max Activating Token Index: 445

Text #10

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.1142. Min Act: -0.0000

Data Index: 363174 (The Pile)

Max Activating Token Index: 726

Text #11

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.1660. Min Act: -0.0000

Data Index: 1625819 (The Pile)

Max Activating Token Index: 262

Text #12

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0769. Min Act: -0.0000

Data Index: 1498596 (The Pile)

Max Activating Token Index: 226

Text #13

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0906. Min Act: -0.0000

Data Index: 894751 (The Pile)

Max Activating Token Index: 404

Text #14

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.0634. Min Act: -0.0000

Data Index: 334258 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 1.7856. Min Range: -1.7856

Max Act: 1.1034. Min Act: -0.0000

Data Index: 143274 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9945. Min Act: -0.0000

Data Index: 422911 (The Pile)

Max Activating Token Index: 723

Text #17

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9952. Min Act: -0.0000

Data Index: 1283082 (The Pile)

Max Activating Token Index: 572

Text #18

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9650. Min Act: -0.0000

Data Index: 97928 (The Pile)

Max Activating Token Index: 473

Text #19

Max Range: 1.7856. Min Range: -1.7856

Max Act: 0.9855. Min Act: -0.0000

Data Index: 551393 (The Pile)

Max Activating Token Index: 235