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

Dataset: The Pile

Neuron 3676 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: 4.5276. Min Range: -4.5276

Max Act: 3.7512. Min Act: -0.0000

Data Index: 1411014 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 4.5276. Min Range: -4.5276

Max Act: 4.5276. Min Act: -0.0000

Data Index: 954753 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 4.5276. Min Range: -4.5276

Max Act: 4.1236. Min Act: -0.0000

Data Index: 220187 (The Pile)

Max Activating Token Index: 607

Text #3

Max Range: 4.5276. Min Range: -4.5276

Max Act: 4.3070. Min Act: -0.0000

Data Index: 406859 (The Pile)

Max Activating Token Index: 215

Text #4

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.5389. Min Act: -0.0000

Data Index: 1993789 (The Pile)

Max Activating Token Index: 800

Text #5

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.3558. Min Act: -0.0000

Data Index: 594185 (The Pile)

Max Activating Token Index: 1013

Text #6

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.5326. Min Act: -0.0000

Data Index: 1553836 (The Pile)

Max Activating Token Index: 694

Text #7

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.2094. Min Act: -0.0000

Data Index: 981352 (The Pile)

Max Activating Token Index: 304

Text #8

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.2956. Min Act: -0.0000

Data Index: 1767580 (The Pile)

Max Activating Token Index: 682

Text #9

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.1296. Min Act: -0.0000

Data Index: 820887 (The Pile)

Max Activating Token Index: 877

Text #10

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.0469. Min Act: -0.0000

Data Index: 1996365 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 4.5276. Min Range: -4.5276

Max Act: 2.7752. Min Act: -0.0000

Data Index: 1685053 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.0511. Min Act: -0.0000

Data Index: 1988600 (The Pile)

Max Activating Token Index: 345

Text #13

Max Range: 4.5276. Min Range: -4.5276

Max Act: 3.0796. Min Act: -0.0000

Data Index: 1784154 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 4.5276. Min Range: -4.5276

Max Act: 1.8016. Min Act: -0.0000

Data Index: 304551 (The Pile)

Max Activating Token Index: 985

Text #15

Max Range: 4.5276. Min Range: -4.5276

Max Act: 2.2787. Min Act: -0.0000

Data Index: 719807 (The Pile)

Max Activating Token Index: 791

Text #16

Max Range: 4.5276. Min Range: -4.5276

Max Act: 2.5685. Min Act: -0.0000

Data Index: 925977 (The Pile)

Max Activating Token Index: 158

Text #17

Max Range: 4.5276. Min Range: -4.5276

Max Act: 2.5128. Min Act: -0.0000

Data Index: 625941 (The Pile)

Max Activating Token Index: 439

Text #18

Max Range: 4.5276. Min Range: -4.5276

Max Act: 2.7695. Min Act: -0.0000

Data Index: 1295389 (The Pile)

Max Activating Token Index: 417

Text #19

Max Range: 4.5276. Min Range: -4.5276

Max Act: 1.7684. Min Act: -0.0000

Data Index: 996202 (The Pile)

Max Activating Token Index: 800