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

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

Neuron 3927 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.4402. Min Act: -0.0000

Data Index: 37972 (C4 (Web Text))

Max Activating Token Index: 117

Text #1

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.3028. Min Act: -0.0000

Data Index: 905300 (C4 (Web Text))

Max Activating Token Index: 111

Text #2

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1996. Min Act: -0.0000

Data Index: 587318 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.2035. Min Act: -0.0000

Data Index: 87973 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1537. Min Act: -0.0000

Data Index: 412154 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0705. Min Act: -0.0000

Data Index: 1022961 (C4 (Web Text))

Max Activating Token Index: 642

Text #6

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0949. Min Act: -0.0000

Data Index: 476609 (C4 (Web Text))

Max Activating Token Index: 272

Text #7

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0938. Min Act: -0.0000

Data Index: 708626 (C4 (Web Text))

Max Activating Token Index: 212

Text #8

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.1739. Min Act: -0.0000

Data Index: 1002764 (C4 (Web Text))

Max Activating Token Index: 883

Text #9

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0441. Min Act: -0.0000

Data Index: 171823 (C4 (Web Text))

Max Activating Token Index: 601

Text #10

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0039. Min Act: -0.0000

Data Index: 875929 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 1.4402. Min Range: -1.4402

Max Act: 1.0066. Min Act: -0.0000

Data Index: 425578 (C4 (Web Text))

Max Activating Token Index: 775

Text #12

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9929. Min Act: -0.0000

Data Index: 704382 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9564. Min Act: -0.0000

Data Index: 1095051 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9879. Min Act: -0.0000

Data Index: 1196007 (C4 (Web Text))

Max Activating Token Index: 599

Text #15

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9454. Min Act: -0.0000

Data Index: 1236215 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9877. Min Act: -0.0000

Data Index: 1257188 (C4 (Web Text))

Max Activating Token Index: 972

Text #17

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9619. Min Act: -0.0000

Data Index: 1173122 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9481. Min Act: -0.0000

Data Index: 709799 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 1.4402. Min Range: -1.4402

Max Act: 0.9812. Min Act: -0.0000

Data Index: 1215040 (C4 (Web Text))

Max Activating Token Index: 817