Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3690 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0860. Min Act: -0.0002

Data Index: 89797 (C4 (Web Text))

Max Activating Token Index: 646

Text #1

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0727. Min Act: -0.0002

Data Index: 370678 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0755. Min Act: -0.0002

Data Index: 1280432 (C4 (Web Text))

Max Activating Token Index: 92

Text #3

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0690. Min Act: -0.0002

Data Index: 312712 (C4 (Web Text))

Max Activating Token Index: 378

Text #4

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0694. Min Act: -0.0002

Data Index: 790588 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0713. Min Act: -0.0002

Data Index: 719338 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0663. Min Act: -0.0002

Data Index: 242920 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1071274 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0681. Min Act: -0.0002

Data Index: 71585 (C4 (Web Text))

Max Activating Token Index: 413

Text #9

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0648. Min Act: -0.0002

Data Index: 484510 (C4 (Web Text))

Max Activating Token Index: 139

Text #10

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0642. Min Act: -0.0002

Data Index: 300700 (C4 (Web Text))

Max Activating Token Index: 41

Text #11

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0642. Min Act: -0.0002

Data Index: 255600 (C4 (Web Text))

Max Activating Token Index: 85

Text #12

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1168206 (C4 (Web Text))

Max Activating Token Index: 802

Text #13

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0614. Min Act: -0.0002

Data Index: 1134799 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1077096 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0615. Min Act: -0.0002

Data Index: 1113914 (C4 (Web Text))

Max Activating Token Index: 687

Text #16

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0605. Min Act: -0.0002

Data Index: 291934 (C4 (Web Text))

Max Activating Token Index: 769

Text #17

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0601. Min Act: -0.0002

Data Index: 405030 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0597. Min Act: -0.0002

Data Index: 1028839 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 0.0860. Min Range: -0.0860

Max Act: 0.0594. Min Act: -0.0002

Data Index: 686395 (C4 (Web Text))

Max Activating Token Index: 865