Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1673 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.4020. Min Act: -0.0003

Data Index: 1109435 (C4 (Web Text))

Max Activating Token Index: 160

Text #1

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.4118. Min Act: -0.0003

Data Index: 680704 (C4 (Web Text))

Max Activating Token Index: 881

Text #2

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.4071. Min Act: -0.0003

Data Index: 832702 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3938. Min Act: -0.0003

Data Index: 1058744 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.4009. Min Act: -0.0003

Data Index: 779777 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.4022. Min Act: -0.0003

Data Index: 1213547 (C4 (Web Text))

Max Activating Token Index: 908

Text #6

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3875. Min Act: -0.0003

Data Index: 452970 (C4 (Web Text))

Max Activating Token Index: 232

Text #7

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3848. Min Act: -0.0003

Data Index: 631904 (C4 (Web Text))

Max Activating Token Index: 119

Text #8

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3963. Min Act: -0.0003

Data Index: 1321405 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3831. Min Act: -0.0003

Data Index: 314591 (C4 (Web Text))

Max Activating Token Index: 800

Text #10

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3802. Min Act: -0.0003

Data Index: 920377 (C4 (Web Text))

Max Activating Token Index: 685

Text #11

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3797. Min Act: -0.0003

Data Index: 640348 (C4 (Web Text))

Max Activating Token Index: 676

Text #12

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3659. Min Act: -0.0003

Data Index: 1087564 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3766. Min Act: -0.0003

Data Index: 1159851 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3761. Min Act: -0.0003

Data Index: 746900 (C4 (Web Text))

Max Activating Token Index: 176

Text #15

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3759. Min Act: -0.0003

Data Index: 886887 (C4 (Web Text))

Max Activating Token Index: 176

Text #16

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3607. Min Act: -0.0003

Data Index: 894699 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3580. Min Act: -0.0003

Data Index: 460239 (C4 (Web Text))

Max Activating Token Index: 669

Text #18

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3668. Min Act: -0.0003

Data Index: 278714 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.4118. Min Range: -0.4118

Max Act: 0.3659. Min Act: -0.0003

Data Index: 555222 (C4 (Web Text))

Max Activating Token Index: 822