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

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

Neuron 1357 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1019. Min Range: -2.1019

Max Act: 2.1019. Min Act: -0.0000

Data Index: 43817 (C4 (Web Text))

Max Activating Token Index: 911

Text #1

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.4215. Min Act: -0.0000

Data Index: 350629 (C4 (Web Text))

Max Activating Token Index: 566

Text #2

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.2811. Min Act: -0.0000

Data Index: 849772 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.2112. Min Act: -0.0000

Data Index: 757881 (C4 (Web Text))

Max Activating Token Index: 565

Text #4

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.2464. Min Act: -0.0001

Data Index: 267627 (C4 (Web Text))

Max Activating Token Index: 241

Text #5

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.1627. Min Act: -0.0000

Data Index: 13800 (C4 (Web Text))

Max Activating Token Index: 652

Text #6

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.1095. Min Act: -0.0000

Data Index: 962406 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.2241. Min Act: -0.0000

Data Index: 920772 (C4 (Web Text))

Max Activating Token Index: 131

Text #8

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.0191. Min Act: -0.0000

Data Index: 1079194 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.1219. Min Act: -0.0000

Data Index: 1000932 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9886. Min Act: -0.0000

Data Index: 914579 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.0211. Min Act: -0.0000

Data Index: 538634 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 2.1019. Min Range: -2.1019

Max Act: 1.0684. Min Act: -0.0000

Data Index: 884425 (C4 (Web Text))

Max Activating Token Index: 833

Text #13

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9511. Min Act: -0.0000

Data Index: 349538 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9409. Min Act: -0.0000

Data Index: 231248 (C4 (Web Text))

Max Activating Token Index: 949

Text #15

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9642. Min Act: -0.0000

Data Index: 648905 (C4 (Web Text))

Max Activating Token Index: 908

Text #16

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9438. Min Act: -0.0000

Data Index: 769169 (C4 (Web Text))

Max Activating Token Index: 971

Text #17

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9138. Min Act: -0.0000

Data Index: 1538810 (Python Code)

Max Activating Token Index: 747

Text #18

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1001985 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 2.1019. Min Range: -2.1019

Max Act: 0.9319. Min Act: -0.0000

Data Index: 96069 (C4 (Web Text))

Max Activating Token Index: 2