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

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

Neuron 2745 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0980. Min Act: -0.0002

Data Index: 687398 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1338445 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0623. Min Act: -0.0003

Data Index: 674912 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0594. Min Act: -0.0002

Data Index: 384051 (C4 (Web Text))

Max Activating Token Index: 114

Text #4

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0576. Min Act: -0.0003

Data Index: 986494 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0518. Min Act: -0.0003

Data Index: 1124809 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0493. Min Act: -0.0003

Data Index: 34169 (C4 (Web Text))

Max Activating Token Index: 207

Text #7

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0483. Min Act: -0.0003

Data Index: 1176039 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0483. Min Act: -0.0003

Data Index: 354103 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0480. Min Act: -0.0003

Data Index: 403344 (C4 (Web Text))

Max Activating Token Index: 282

Text #10

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0472. Min Act: -0.0003

Data Index: 100228 (C4 (Web Text))

Max Activating Token Index: 921

Text #11

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0441. Min Act: -0.0002

Data Index: 533592 (C4 (Web Text))

Max Activating Token Index: 680

Text #12

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0458. Min Act: -0.0003

Data Index: 55586 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0431. Min Act: -0.0003

Data Index: 934607 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0428. Min Act: -0.0002

Data Index: 1332661 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0417. Min Act: -0.0003

Data Index: 936820 (C4 (Web Text))

Max Activating Token Index: 127

Text #16

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0434. Min Act: -0.0003

Data Index: 98768 (C4 (Web Text))

Max Activating Token Index: 823

Text #17

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0424. Min Act: -0.0003

Data Index: 570099 (C4 (Web Text))

Max Activating Token Index: 164

Text #18

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0427. Min Act: -0.0002

Data Index: 39066 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.0980. Min Range: -0.0980

Max Act: 0.0418. Min Act: -0.0003

Data Index: 47178 (C4 (Web Text))

Max Activating Token Index: 30