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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5072 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3796. Min Range: -1.3796

Max Act: 1.3796. Min Act: -0.0000

Data Index: 976500 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9446. Min Act: -0.0000

Data Index: 1111608 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9169. Min Act: -0.0000

Data Index: 345595 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1171129 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9014. Min Act: -0.0000

Data Index: 991552 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8958. Min Act: -0.0000

Data Index: 639452 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.9155. Min Act: -0.0000

Data Index: 793579 (C4 (Web Text))

Max Activating Token Index: 742

Text #7

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8770. Min Act: -0.0000

Data Index: 710782 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8990. Min Act: -0.0000

Data Index: 216928 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8701. Min Act: -0.0000

Data Index: 1105785 (C4 (Web Text))

Max Activating Token Index: 356

Text #10

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8653. Min Act: -0.0000

Data Index: 27297 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8934. Min Act: -0.0000

Data Index: 1230283 (C4 (Web Text))

Max Activating Token Index: 55

Text #12

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8870. Min Act: -0.0000

Data Index: 686844 (C4 (Web Text))

Max Activating Token Index: 54

Text #13

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8474. Min Act: -0.0000

Data Index: 108160 (C4 (Web Text))

Max Activating Token Index: 115

Text #14

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8254. Min Act: -0.0000

Data Index: 927205 (C4 (Web Text))

Max Activating Token Index: 15

Text #15

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8498. Min Act: -0.0000

Data Index: 497779 (C4 (Web Text))

Max Activating Token Index: 85

Text #16

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1211587 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8685. Min Act: -0.0000

Data Index: 468081 (C4 (Web Text))

Max Activating Token Index: 53

Text #18

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.7607. Min Act: -0.0000

Data Index: 818913 (C4 (Web Text))

Max Activating Token Index: 105

Text #19

Max Range: 1.3796. Min Range: -1.3796

Max Act: 0.8661. Min Act: -0.0000

Data Index: 1356866 (C4 (Web Text))

Max Activating Token Index: 51