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

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

Neuron 1960 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1040. Min Act: -0.0005

Data Index: 791842 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1043. Min Act: -0.0005

Data Index: 1010890 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1041. Min Act: -0.0005

Data Index: 576070 (C4 (Web Text))

Max Activating Token Index: 710

Text #3

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1024. Min Act: -0.0005

Data Index: 717778 (C4 (Web Text))

Max Activating Token Index: 736

Text #4

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.1013. Min Act: -0.0005

Data Index: 495855 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0979. Min Act: -0.0005

Data Index: 1098028 (C4 (Web Text))

Max Activating Token Index: 229

Text #6

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0971. Min Act: -0.0005

Data Index: 21959 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0904. Min Act: -0.0005

Data Index: 1141943 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0935. Min Act: -0.0005

Data Index: 73929 (C4 (Web Text))

Max Activating Token Index: 178

Text #9

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0949. Min Act: -0.0005

Data Index: 1043605 (C4 (Web Text))

Max Activating Token Index: 254

Text #10

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0907. Min Act: -0.0005

Data Index: 271962 (C4 (Web Text))

Max Activating Token Index: 267

Text #11

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0967. Min Act: -0.0005

Data Index: 813316 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0934. Min Act: -0.0005

Data Index: 254915 (C4 (Web Text))

Max Activating Token Index: 731

Text #13

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0885. Min Act: -0.0005

Data Index: 241446 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0913. Min Act: -0.0005

Data Index: 165676 (C4 (Web Text))

Max Activating Token Index: 274

Text #15

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0907. Min Act: -0.0005

Data Index: 416429 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0798. Min Act: -0.0005

Data Index: 280407 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0884. Min Act: -0.0005

Data Index: 831211 (C4 (Web Text))

Max Activating Token Index: 979

Text #18

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0851. Min Act: -0.0005

Data Index: 479760 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.1043. Min Range: -0.1043

Max Act: 0.0814. Min Act: -0.0005

Data Index: 386196 (C4 (Web Text))

Max Activating Token Index: 287