Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2789 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.9180. Min Act: -0.0002

Data Index: 708591 (C4 (Web Text))

Max Activating Token Index: 220

Text #1

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.9147. Min Act: -0.0001

Data Index: 1146105 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.8436. Min Act: -0.0002

Data Index: 606038 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.8666. Min Act: -0.0002

Data Index: 713481 (C4 (Web Text))

Max Activating Token Index: 171

Text #4

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7795. Min Act: -0.0002

Data Index: 1285934 (C4 (Web Text))

Max Activating Token Index: 978

Text #5

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7522. Min Act: -0.0001

Data Index: 1302314 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7977. Min Act: -0.0001

Data Index: 809685 (C4 (Web Text))

Max Activating Token Index: 801

Text #7

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7396. Min Act: -0.0001

Data Index: 733054 (C4 (Web Text))

Max Activating Token Index: 1014

Text #8

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7645. Min Act: -0.0001

Data Index: 107511 (C4 (Web Text))

Max Activating Token Index: 596

Text #9

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7131. Min Act: -0.0001

Data Index: 309040 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7079. Min Act: -0.0002

Data Index: 837990 (C4 (Web Text))

Max Activating Token Index: 1000

Text #11

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6999. Min Act: -0.0002

Data Index: 609122 (C4 (Web Text))

Max Activating Token Index: 188

Text #12

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7194. Min Act: -0.0002

Data Index: 643957 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7447. Min Act: -0.0001

Data Index: 53030 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7111. Min Act: -0.0002

Data Index: 518737 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7229. Min Act: -0.0001

Data Index: 266793 (C4 (Web Text))

Max Activating Token Index: 498

Text #16

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6757. Min Act: -0.0002

Data Index: 254628 (C4 (Web Text))

Max Activating Token Index: 864

Text #17

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.7154. Min Act: -0.0002

Data Index: 356135 (C4 (Web Text))

Max Activating Token Index: 82

Text #18

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6474. Min Act: -0.0001

Data Index: 275178 (C4 (Web Text))

Max Activating Token Index: 610

Text #19

Max Range: 0.9180. Min Range: -0.9180

Max Act: 0.6894. Min Act: -0.0001

Data Index: 996726 (C4 (Web Text))

Max Activating Token Index: 899