Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 90 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0145. Min Range: -1.0145

Max Act: 1.0145. Min Act: -0.0000

Data Index: 95329 (C4 (Web Text))

Max Activating Token Index: 804

Text #1

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.9791. Min Act: -0.0000

Data Index: 661234 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8363. Min Act: -0.0000

Data Index: 1124100 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7998. Min Act: -0.0000

Data Index: 1181974 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8772. Min Act: -0.0000

Data Index: 780135 (C4 (Web Text))

Max Activating Token Index: 377

Text #5

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7860. Min Act: -0.0000

Data Index: 1092150 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8013. Min Act: -0.0000

Data Index: 132397 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7983. Min Act: -0.0000

Data Index: 330456 (C4 (Web Text))

Max Activating Token Index: 548

Text #8

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7016. Min Act: -0.0000

Data Index: 193212 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7601. Min Act: -0.0000

Data Index: 486312 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.8036. Min Act: -0.0000

Data Index: 1140702 (C4 (Web Text))

Max Activating Token Index: 162

Text #11

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7315. Min Act: -0.0000

Data Index: 69142 (C4 (Web Text))

Max Activating Token Index: 181

Text #12

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7937. Min Act: -0.0000

Data Index: 1138847 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.7871. Min Act: -0.0000

Data Index: 1022072 (C4 (Web Text))

Max Activating Token Index: 907

Text #14

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.6780. Min Act: -0.0000

Data Index: 689117 (C4 (Web Text))

Max Activating Token Index: 869

Text #15

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.6911. Min Act: -0.0000

Data Index: 34270 (C4 (Web Text))

Max Activating Token Index: 54

Text #16

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.6947. Min Act: -0.0000

Data Index: 822366 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.6418. Min Act: -0.0000

Data Index: 916505 (C4 (Web Text))

Max Activating Token Index: 974

Text #18

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.6179. Min Act: -0.0000

Data Index: 147068 (C4 (Web Text))

Max Activating Token Index: 389

Text #19

Max Range: 1.0145. Min Range: -1.0145

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1237833 (C4 (Web Text))

Max Activating Token Index: 633