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

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

Neuron 329 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0979. Min Act: -0.0002

Data Index: 760841 (C4 (Web Text))

Max Activating Token Index: 960

Text #1

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0823. Min Act: -0.0002

Data Index: 118263 (C4 (Web Text))

Max Activating Token Index: 542

Text #2

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0836. Min Act: -0.0002

Data Index: 448130 (C4 (Web Text))

Max Activating Token Index: 917

Text #3

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0803. Min Act: -0.0002

Data Index: 484323 (C4 (Web Text))

Max Activating Token Index: 639

Text #4

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0794. Min Act: -0.0002

Data Index: 97183 (C4 (Web Text))

Max Activating Token Index: 306

Text #5

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0767. Min Act: -0.0002

Data Index: 1110089 (C4 (Web Text))

Max Activating Token Index: 538

Text #6

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0740. Min Act: -0.0002

Data Index: 1243793 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0769. Min Act: -0.0002

Data Index: 35195 (C4 (Web Text))

Max Activating Token Index: 500

Text #8

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0753. Min Act: -0.0002

Data Index: 1349074 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0867. Min Act: -0.0001

Data Index: 157829 (C4 (Web Text))

Max Activating Token Index: 860

Text #10

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0676. Min Act: -0.0001

Data Index: 759614 (C4 (Web Text))

Max Activating Token Index: 659

Text #11

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0723. Min Act: -0.0002

Data Index: 499610 (C4 (Web Text))

Max Activating Token Index: 666

Text #12

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0771. Min Act: -0.0001

Data Index: 840307 (C4 (Web Text))

Max Activating Token Index: 286

Text #13

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1222915 (C4 (Web Text))

Max Activating Token Index: 53

Text #14

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1157388 (C4 (Web Text))

Max Activating Token Index: 357

Text #15

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0765. Min Act: -0.0002

Data Index: 1312835 (C4 (Web Text))

Max Activating Token Index: 99

Text #16

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0733. Min Act: -0.0001

Data Index: 857858 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0738. Min Act: -0.0001

Data Index: 607291 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0728. Min Act: -0.0001

Data Index: 384116 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 0.0979. Min Range: -0.0979

Max Act: 0.0717. Min Act: -0.0002

Data Index: 684046 (C4 (Web Text))

Max Activating Token Index: 894