Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1793 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1729. Min Range: -1.1729

Max Act: 1.1472. Min Act: -0.0000

Data Index: 262928 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 1.1729. Min Range: -1.1729

Max Act: 1.1281. Min Act: -0.0000

Data Index: 105695 (C4 (Web Text))

Max Activating Token Index: 643

Text #2

Max Range: 1.1729. Min Range: -1.1729

Max Act: 1.1729. Min Act: -0.0000

Data Index: 1102276 (C4 (Web Text))

Max Activating Token Index: 144

Text #3

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.9960. Min Act: -0.0000

Data Index: 44714 (C4 (Web Text))

Max Activating Token Index: 147

Text #4

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.9987. Min Act: -0.0000

Data Index: 283154 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.9587. Min Act: -0.0000

Data Index: 756041 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.9285. Min Act: -0.0000

Data Index: 322377 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.9336. Min Act: -0.0000

Data Index: 1067265 (C4 (Web Text))

Max Activating Token Index: 801

Text #8

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8416. Min Act: -0.0000

Data Index: 501700 (C4 (Web Text))

Max Activating Token Index: 137

Text #9

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8912. Min Act: -0.0000

Data Index: 1027168 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8848. Min Act: -0.0000

Data Index: 534482 (C4 (Web Text))

Max Activating Token Index: 148

Text #11

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.9077. Min Act: -0.0000

Data Index: 1080794 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8773. Min Act: -0.0000

Data Index: 175280 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8753. Min Act: -0.0000

Data Index: 1127242 (C4 (Web Text))

Max Activating Token Index: 57

Text #14

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8527. Min Act: -0.0000

Data Index: 806048 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8395. Min Act: -0.0000

Data Index: 380665 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8421. Min Act: -0.0000

Data Index: 612677 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8612. Min Act: -0.0000

Data Index: 232455 (C4 (Web Text))

Max Activating Token Index: 167

Text #18

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8333. Min Act: -0.0000

Data Index: 555247 (C4 (Web Text))

Max Activating Token Index: 741

Text #19

Max Range: 1.1729. Min Range: -1.1729

Max Act: 0.8539. Min Act: -0.0000

Data Index: 12828 (C4 (Web Text))

Max Activating Token Index: 819