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

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

Neuron 3537 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.8044. Min Act: -0.0001

Data Index: 209659 (C4 (Web Text))

Max Activating Token Index: 289

Text #1

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.8058. Min Act: -0.0001

Data Index: 472815 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7683. Min Act: -0.0001

Data Index: 970047 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7243. Min Act: -0.0001

Data Index: 1083049 (C4 (Web Text))

Max Activating Token Index: 197

Text #4

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7527. Min Act: -0.0001

Data Index: 772741 (C4 (Web Text))

Max Activating Token Index: 967

Text #5

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7507. Min Act: -0.0001

Data Index: 64389 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7184. Min Act: -0.0001

Data Index: 754661 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6375. Min Act: -0.0001

Data Index: 757959 (C4 (Web Text))

Max Activating Token Index: 667

Text #8

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6610. Min Act: -0.0001

Data Index: 514372 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7259. Min Act: -0.0001

Data Index: 550949 (C4 (Web Text))

Max Activating Token Index: 87

Text #10

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6503. Min Act: -0.0001

Data Index: 1183392 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6474. Min Act: -0.0001

Data Index: 282195 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6864. Min Act: -0.0001

Data Index: 581290 (C4 (Web Text))

Max Activating Token Index: 927

Text #13

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6827. Min Act: -0.0001

Data Index: 120449 (C4 (Web Text))

Max Activating Token Index: 454

Text #14

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6710. Min Act: -0.0001

Data Index: 1136014 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6831. Min Act: -0.0001

Data Index: 683096 (C4 (Web Text))

Max Activating Token Index: 611

Text #16

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6243. Min Act: -0.0001

Data Index: 591378 (C4 (Web Text))

Max Activating Token Index: 34

Text #17

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6592. Min Act: -0.0001

Data Index: 200748 (C4 (Web Text))

Max Activating Token Index: 5

Text #18

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.6153. Min Act: -0.0001

Data Index: 1527701 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 0.8058. Min Range: -0.8058

Max Act: 0.7391. Min Act: -0.0001

Data Index: 1039990 (C4 (Web Text))

Max Activating Token Index: 921