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

Dataset: The Pile

Neuron 4401 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: 1.9110. Min Range: -1.9110

Max Act: 1.9110. Min Act: -0.0000

Data Index: 1952554 (The Pile)

Max Activating Token Index: 954

Text #1

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.8981. Min Act: -0.0000

Data Index: 1480369 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.8615. Min Act: -0.0000

Data Index: 1062843 (The Pile)

Max Activating Token Index: 795

Text #3

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.7536. Min Act: -0.0000

Data Index: 325616 (The Pile)

Max Activating Token Index: 966

Text #4

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.7427. Min Act: -0.0000

Data Index: 136692 (The Pile)

Max Activating Token Index: 917

Text #5

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.7742. Min Act: -0.0000

Data Index: 1148402 (The Pile)

Max Activating Token Index: 697

Text #6

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.7287. Min Act: -0.0000

Data Index: 696058 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.7031. Min Act: -0.0000

Data Index: 329645 (The Pile)

Max Activating Token Index: 517

Text #8

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.6981. Min Act: -0.0000

Data Index: 527748 (The Pile)

Max Activating Token Index: 718

Text #9

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.5893. Min Act: -0.0000

Data Index: 771748 (The Pile)

Max Activating Token Index: 14

Text #10

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.6856. Min Act: -0.0000

Data Index: 1224528 (The Pile)

Max Activating Token Index: 88

Text #11

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.6783. Min Act: -0.0000

Data Index: 36819 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.5827. Min Act: -0.0000

Data Index: 635009 (The Pile)

Max Activating Token Index: 1011

Text #13

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.6469. Min Act: -0.0000

Data Index: 469050 (The Pile)

Max Activating Token Index: 296

Text #14

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.5381. Min Act: -0.0000

Data Index: 1258317 (The Pile)

Max Activating Token Index: 926

Text #15

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.6509. Min Act: -0.0000

Data Index: 826817 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.6518. Min Act: -0.0000

Data Index: 247664 (The Pile)

Max Activating Token Index: 790

Text #17

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.6391. Min Act: -0.0000

Data Index: 1269104 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.5914. Min Act: -0.0000

Data Index: 1373402 (The Pile)

Max Activating Token Index: 402

Text #19

Max Range: 1.9110. Min Range: -1.9110

Max Act: 1.5034. Min Act: -0.0000

Data Index: 1117421 (The Pile)

Max Activating Token Index: 101