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

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

Neuron 4074 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.6274. Min Act: -0.0000

Data Index: 146170 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5375. Min Act: -0.0000

Data Index: 585501 (C4 (Web Text))

Max Activating Token Index: 294

Text #2

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5518. Min Act: -0.0000

Data Index: 210905 (C4 (Web Text))

Max Activating Token Index: 997

Text #3

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.5003. Min Act: -0.0000

Data Index: 756332 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4908. Min Act: -0.0000

Data Index: 120490 (C4 (Web Text))

Max Activating Token Index: 349

Text #5

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4740. Min Act: -0.0000

Data Index: 1009842 (C4 (Web Text))

Max Activating Token Index: 20

Text #6

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4474. Min Act: -0.0000

Data Index: 111549 (C4 (Web Text))

Max Activating Token Index: 328

Text #7

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4500. Min Act: -0.0000

Data Index: 409886 (C4 (Web Text))

Max Activating Token Index: 196

Text #8

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4456. Min Act: -0.0000

Data Index: 310123 (C4 (Web Text))

Max Activating Token Index: 597

Text #9

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4681. Min Act: -0.0000

Data Index: 476820 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4494. Min Act: -0.0000

Data Index: 190814 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4192. Min Act: -0.0000

Data Index: 111553 (C4 (Web Text))

Max Activating Token Index: 604

Text #12

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4046. Min Act: -0.0000

Data Index: 1028386 (C4 (Web Text))

Max Activating Token Index: 451

Text #13

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4036. Min Act: -0.0000

Data Index: 870815 (C4 (Web Text))

Max Activating Token Index: 816

Text #14

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.3945. Min Act: -0.0000

Data Index: 1290137 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.3895. Min Act: -0.0000

Data Index: 1137973 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.3633. Min Act: -0.0000

Data Index: 823595 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.3704. Min Act: -0.0000

Data Index: 440071 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.3839. Min Act: -0.0000

Data Index: 774317 (C4 (Web Text))

Max Activating Token Index: 6

Text #19

Max Range: 0.6274. Min Range: -0.6274

Max Act: 0.4071. Min Act: -0.0000

Data Index: 812434 (C4 (Web Text))

Max Activating Token Index: 884