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

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

Neuron 198 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1149. Min Act: -0.0000

Data Index: 705988 (C4 (Web Text))

Max Activating Token Index: 594

Text #1

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1060. Min Act: -0.0000

Data Index: 122676 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1215074 (C4 (Web Text))

Max Activating Token Index: 108

Text #3

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1096. Min Act: -0.0000

Data Index: 559281 (C4 (Web Text))

Max Activating Token Index: 261

Text #4

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0975. Min Act: -0.0000

Data Index: 105560 (C4 (Web Text))

Max Activating Token Index: 192

Text #5

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0938. Min Act: -0.0000

Data Index: 205647 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0872. Min Act: -0.0000

Data Index: 639940 (C4 (Web Text))

Max Activating Token Index: 609

Text #7

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.1058. Min Act: -0.0000

Data Index: 131470 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0935. Min Act: -0.0001

Data Index: 213759 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0894. Min Act: -0.0001

Data Index: 1236644 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0892. Min Act: -0.0001

Data Index: 1090696 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0906. Min Act: -0.0000

Data Index: 194912 (C4 (Web Text))

Max Activating Token Index: 7

Text #12

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0799. Min Act: -0.0000

Data Index: 252008 (C4 (Web Text))

Max Activating Token Index: 677

Text #13

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0929. Min Act: -0.0000

Data Index: 616989 (C4 (Web Text))

Max Activating Token Index: 276

Text #14

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0822. Min Act: -0.0001

Data Index: 302003 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0819. Min Act: -0.0000

Data Index: 1027312 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0820. Min Act: -0.0001

Data Index: 712508 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1271034 (C4 (Web Text))

Max Activating Token Index: 677

Text #18

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0867. Min Act: -0.0000

Data Index: 296133 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 0.1149. Min Range: -0.1149

Max Act: 0.0759. Min Act: -0.0001

Data Index: 1048262 (C4 (Web Text))

Max Activating Token Index: 244