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

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

Neuron 21 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1059. Min Act: -0.0001

Data Index: 140361 (C4 (Web Text))

Max Activating Token Index: 199

Text #1

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1113. Min Act: -0.0001

Data Index: 1351706 (C4 (Web Text))

Max Activating Token Index: 962

Text #2

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1048. Min Act: -0.0001

Data Index: 1088986 (C4 (Web Text))

Max Activating Token Index: 402

Text #3

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0964. Min Act: -0.0001

Data Index: 136957 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0982. Min Act: -0.0001

Data Index: 194634 (C4 (Web Text))

Max Activating Token Index: 10

Text #5

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1049. Min Act: -0.0001

Data Index: 985437 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0933. Min Act: -0.0001

Data Index: 700556 (C4 (Web Text))

Max Activating Token Index: 804

Text #7

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1036. Min Act: -0.0001

Data Index: 480306 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1349850 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1317002 (C4 (Web Text))

Max Activating Token Index: 955

Text #10

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0952. Min Act: -0.0001

Data Index: 966179 (C4 (Web Text))

Max Activating Token Index: 857

Text #11

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.1009. Min Act: -0.0001

Data Index: 117510 (C4 (Web Text))

Max Activating Token Index: 533

Text #12

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1079902 (C4 (Web Text))

Max Activating Token Index: 36

Text #13

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0934. Min Act: -0.0001

Data Index: 1208365 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0893. Min Act: -0.0001

Data Index: 630783 (C4 (Web Text))

Max Activating Token Index: 700

Text #15

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0932. Min Act: -0.0001

Data Index: 901771 (C4 (Web Text))

Max Activating Token Index: 907

Text #16

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0983. Min Act: -0.0001

Data Index: 532048 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1023386 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0938. Min Act: -0.0001

Data Index: 522370 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.1113. Min Range: -0.1113

Max Act: 0.0919. Min Act: -0.0001

Data Index: 1305849 (C4 (Web Text))

Max Activating Token Index: 520