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

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

Neuron 3906 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: 0.1022. Min Range: -0.1022

Max Act: 0.1022. Min Act: -0.0002

Data Index: 714955 (C4 (Web Text))

Max Activating Token Index: 115

Text #1

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0729. Min Act: -0.0002

Data Index: 1067051 (C4 (Web Text))

Max Activating Token Index: 405

Text #2

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0728. Min Act: -0.0002

Data Index: 1004282 (C4 (Web Text))

Max Activating Token Index: 170

Text #3

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0615. Min Act: -0.0002

Data Index: 654301 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0645. Min Act: -0.0002

Data Index: 1093954 (C4 (Web Text))

Max Activating Token Index: 795

Text #5

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0644. Min Act: -0.0002

Data Index: 1100431 (C4 (Web Text))

Max Activating Token Index: 200

Text #6

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0628. Min Act: -0.0002

Data Index: 5889 (C4 (Web Text))

Max Activating Token Index: 326

Text #7

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0629. Min Act: -0.0002

Data Index: 474408 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0608. Min Act: -0.0002

Data Index: 651658 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1446774 (Python Code)

Max Activating Token Index: 888

Text #10

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0560. Min Act: -0.0002

Data Index: 1143667 (C4 (Web Text))

Max Activating Token Index: 768

Text #11

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1230041 (C4 (Web Text))

Max Activating Token Index: 396

Text #12

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0558. Min Act: -0.0002

Data Index: 279723 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1221632 (C4 (Web Text))

Max Activating Token Index: 541

Text #14

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0548. Min Act: -0.0002

Data Index: 522948 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0587. Min Act: -0.0002

Data Index: 946796 (C4 (Web Text))

Max Activating Token Index: 543

Text #16

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0587. Min Act: -0.0002

Data Index: 725030 (C4 (Web Text))

Max Activating Token Index: 106

Text #17

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0580. Min Act: -0.0002

Data Index: 907790 (C4 (Web Text))

Max Activating Token Index: 690

Text #18

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0552. Min Act: -0.0002

Data Index: 1263552 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.1022. Min Range: -0.1022

Max Act: 0.0532. Min Act: -0.0002

Data Index: 255668 (C4 (Web Text))

Max Activating Token Index: 105