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

Dataset: The Pile

Neuron 2878 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.4329. Min Act: -0.0000

Data Index: 1429308 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.1574. Min Act: -0.0000

Data Index: 927650 (The Pile)

Max Activating Token Index: 291

Text #2

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.0560. Min Act: -0.0000

Data Index: 1585949 (The Pile)

Max Activating Token Index: 121

Text #3

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.0299. Min Act: -0.0000

Data Index: 1332576 (The Pile)

Max Activating Token Index: 369

Text #4

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9504. Min Act: -0.0000

Data Index: 1900181 (The Pile)

Max Activating Token Index: 667

Text #5

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.0106. Min Act: -0.0000

Data Index: 1124329 (The Pile)

Max Activating Token Index: 797

Text #6

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9715. Min Act: -0.0001

Data Index: 1808623 (The Pile)

Max Activating Token Index: 144

Text #7

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9668. Min Act: -0.0000

Data Index: 861721 (The Pile)

Max Activating Token Index: 397

Text #8

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1274894 (The Pile)

Max Activating Token Index: 415

Text #9

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9456. Min Act: -0.0000

Data Index: 611788 (The Pile)

Max Activating Token Index: 291

Text #10

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.8791. Min Act: -0.0000

Data Index: 988973 (The Pile)

Max Activating Token Index: 693

Text #11

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9259. Min Act: -0.0000

Data Index: 1736050 (The Pile)

Max Activating Token Index: 137

Text #12

Max Range: 1.4329. Min Range: -1.4329

Max Act: 1.0244. Min Act: -0.0001

Data Index: 662574 (The Pile)

Max Activating Token Index: 237

Text #13

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9566. Min Act: -0.0000

Data Index: 718517 (The Pile)

Max Activating Token Index: 280

Text #14

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.7959. Min Act: -0.0000

Data Index: 1451047 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.8861. Min Act: -0.0000

Data Index: 313464 (The Pile)

Max Activating Token Index: 522

Text #16

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1786256 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.9957. Min Act: -0.0001

Data Index: 1016665 (The Pile)

Max Activating Token Index: 688

Text #18

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.8799. Min Act: -0.0000

Data Index: 1709340 (The Pile)

Max Activating Token Index: 102

Text #19

Max Range: 1.4329. Min Range: -1.4329

Max Act: 0.8757. Min Act: -0.0000

Data Index: 1992675 (The Pile)

Max Activating Token Index: 190