Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1466 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.1010. Min Act: -0.0003

Data Index: 1065778 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0977. Min Act: -0.0003

Data Index: 620836 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0961. Min Act: -0.0004

Data Index: 419857 (C4 (Web Text))

Max Activating Token Index: 22

Text #3

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0925. Min Act: -0.0004

Data Index: 213527 (C4 (Web Text))

Max Activating Token Index: 166

Text #4

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0956. Min Act: -0.0004

Data Index: 554709 (C4 (Web Text))

Max Activating Token Index: 29

Text #5

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0953. Min Act: -0.0003

Data Index: 453095 (C4 (Web Text))

Max Activating Token Index: 39

Text #6

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0904. Min Act: -0.0003

Data Index: 405481 (C4 (Web Text))

Max Activating Token Index: 664

Text #7

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0864. Min Act: -0.0003

Data Index: 1215859 (C4 (Web Text))

Max Activating Token Index: 291

Text #8

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0896. Min Act: -0.0003

Data Index: 1006940 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0902. Min Act: -0.0003

Data Index: 1055179 (C4 (Web Text))

Max Activating Token Index: 575

Text #10

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0878. Min Act: -0.0004

Data Index: 1203875 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0863. Min Act: -0.0003

Data Index: 420066 (C4 (Web Text))

Max Activating Token Index: 860

Text #12

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0832. Min Act: -0.0003

Data Index: 1025723 (C4 (Web Text))

Max Activating Token Index: 173

Text #13

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0839. Min Act: -0.0003

Data Index: 621543 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0873. Min Act: -0.0003

Data Index: 789364 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0859. Min Act: -0.0003

Data Index: 523092 (C4 (Web Text))

Max Activating Token Index: 134

Text #16

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0857. Min Act: -0.0003

Data Index: 526304 (C4 (Web Text))

Max Activating Token Index: 23

Text #17

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0845. Min Act: -0.0003

Data Index: 367394 (C4 (Web Text))

Max Activating Token Index: 277

Text #18

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0834. Min Act: -0.0003

Data Index: 827390 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 0.1010. Min Range: -0.1010

Max Act: 0.0873. Min Act: -0.0003

Data Index: 512000 (C4 (Web Text))

Max Activating Token Index: 120