Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 426 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0005

Data Index: 303049 (C4 (Web Text))

Max Activating Token Index: 611

Text #1

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0047. Min Act: -0.0005

Data Index: 246577 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0042. Min Act: -0.0006

Data Index: 1038449 (C4 (Web Text))

Max Activating Token Index: 991

Text #3

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0042. Min Act: -0.0005

Data Index: 423739 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0041. Min Act: -0.0005

Data Index: 349282 (C4 (Web Text))

Max Activating Token Index: 302

Text #5

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0040. Min Act: -0.0005

Data Index: 430162 (C4 (Web Text))

Max Activating Token Index: 1019

Text #6

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0039. Min Act: -0.0006

Data Index: 163089 (C4 (Web Text))

Max Activating Token Index: 703

Text #7

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0038. Min Act: -0.0005

Data Index: 984064 (C4 (Web Text))

Max Activating Token Index: 574

Text #8

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0038. Min Act: -0.0005

Data Index: 1138805 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0005

Data Index: 187641 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0005

Data Index: 1110733 (C4 (Web Text))

Max Activating Token Index: 441

Text #11

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 749310 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0005

Data Index: 512367 (C4 (Web Text))

Max Activating Token Index: 909

Text #13

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0005

Data Index: 1166008 (C4 (Web Text))

Max Activating Token Index: 452

Text #14

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0005

Data Index: 215739 (C4 (Web Text))

Max Activating Token Index: 533

Text #15

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0005

Data Index: 1234596 (C4 (Web Text))

Max Activating Token Index: 699

Text #16

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0037. Min Act: -0.0006

Data Index: 415142 (C4 (Web Text))

Max Activating Token Index: 157

Text #17

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0006

Data Index: 330006 (C4 (Web Text))

Max Activating Token Index: 833

Text #18

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0005

Data Index: 335899 (C4 (Web Text))

Max Activating Token Index: 693

Text #19

Max Range: 0.0047. Min Range: -0.0047

Max Act: 0.0036. Min Act: -0.0005

Data Index: 641783 (C4 (Web Text))

Max Activating Token Index: 702