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

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

Neuron 1685 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0863. Min Act: -0.0003

Data Index: 110043 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0811. Min Act: -0.0003

Data Index: 349494 (C4 (Web Text))

Max Activating Token Index: 480

Text #2

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0746. Min Act: -0.0003

Data Index: 271545 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0711. Min Act: -0.0003

Data Index: 1104061 (C4 (Web Text))

Max Activating Token Index: 838

Text #4

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0681. Min Act: -0.0003

Data Index: 50687 (C4 (Web Text))

Max Activating Token Index: 73

Text #5

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1138265 (C4 (Web Text))

Max Activating Token Index: 510

Text #6

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0697. Min Act: -0.0003

Data Index: 16412 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0774. Min Act: -0.0003

Data Index: 209341 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0643. Min Act: -0.0003

Data Index: 928027 (C4 (Web Text))

Max Activating Token Index: 93

Text #9

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0607. Min Act: -0.0004

Data Index: 218658 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0654. Min Act: -0.0003

Data Index: 138832 (C4 (Web Text))

Max Activating Token Index: 116

Text #11

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0624. Min Act: -0.0003

Data Index: 736616 (C4 (Web Text))

Max Activating Token Index: 752

Text #12

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0628. Min Act: -0.0003

Data Index: 346445 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0649. Min Act: -0.0003

Data Index: 947626 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0623. Min Act: -0.0003

Data Index: 1297817 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0644. Min Act: -0.0003

Data Index: 266217 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0640. Min Act: -0.0003

Data Index: 1026685 (C4 (Web Text))

Max Activating Token Index: 42

Text #17

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0594. Min Act: -0.0003

Data Index: 596406 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0658. Min Act: -0.0003

Data Index: 1240300 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 0.0863. Min Range: -0.0863

Max Act: 0.0665. Min Act: -0.0003

Data Index: 18330 (C4 (Web Text))

Max Activating Token Index: 136