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

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

Neuron 4646 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: 0.1162. Min Range: -0.1162

Max Act: 0.1162. Min Act: -0.0001

Data Index: 861421 (C4 (Web Text))

Max Activating Token Index: 68

Text #1

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1070. Min Act: -0.0000

Data Index: 581349 (C4 (Web Text))

Max Activating Token Index: 527

Text #2

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1174048 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1027. Min Act: -0.0001

Data Index: 13992 (C4 (Web Text))

Max Activating Token Index: 143

Text #4

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0965. Min Act: -0.0000

Data Index: 972783 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1071. Min Act: -0.0000

Data Index: 1322830 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0991. Min Act: -0.0000

Data Index: 737825 (C4 (Web Text))

Max Activating Token Index: 90

Text #7

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.1030. Min Act: -0.0000

Data Index: 604083 (C4 (Web Text))

Max Activating Token Index: 1005

Text #8

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0977. Min Act: -0.0000

Data Index: 41500 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0957. Min Act: -0.0001

Data Index: 679896 (C4 (Web Text))

Max Activating Token Index: 710

Text #10

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1118604 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0942. Min Act: -0.0001

Data Index: 1249186 (C4 (Web Text))

Max Activating Token Index: 422

Text #12

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0928. Min Act: -0.0000

Data Index: 260491 (C4 (Web Text))

Max Activating Token Index: 507

Text #13

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1028560 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0980. Min Act: -0.0000

Data Index: 740111 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0878. Min Act: -0.0000

Data Index: 448967 (C4 (Web Text))

Max Activating Token Index: 187

Text #16

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0892. Min Act: -0.0001

Data Index: 890617 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0921. Min Act: -0.0000

Data Index: 664355 (C4 (Web Text))

Max Activating Token Index: 284

Text #18

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1057310 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.1162. Min Range: -0.1162

Max Act: 0.0950. Min Act: -0.0000

Data Index: 1149394 (C4 (Web Text))

Max Activating Token Index: 195