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

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

Neuron 3317 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3632. Min Act: -0.0001

Data Index: 1183867 (C4 (Web Text))

Max Activating Token Index: 854

Text #1

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.4035. Min Act: -0.0001

Data Index: 95605 (C4 (Web Text))

Max Activating Token Index: 357

Text #2

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3053. Min Act: -0.0001

Data Index: 647906 (C4 (Web Text))

Max Activating Token Index: 174

Text #3

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2305. Min Act: -0.0001

Data Index: 722511 (C4 (Web Text))

Max Activating Token Index: 693

Text #4

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.3928. Min Act: -0.0001

Data Index: 258236 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.2016. Min Act: -0.0001

Data Index: 305958 (C4 (Web Text))

Max Activating Token Index: 279

Text #6

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1883. Min Act: -0.0001

Data Index: 1011252 (C4 (Web Text))

Max Activating Token Index: 560

Text #7

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1271. Min Act: -0.0001

Data Index: 307748 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1908. Min Act: -0.0001

Data Index: 1343036 (C4 (Web Text))

Max Activating Token Index: 419

Text #9

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1589. Min Act: -0.0001

Data Index: 968705 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1370. Min Act: -0.0001

Data Index: 665823 (C4 (Web Text))

Max Activating Token Index: 646

Text #11

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1027. Min Act: -0.0001

Data Index: 1086516 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1484. Min Act: -0.0001

Data Index: 1076255 (C4 (Web Text))

Max Activating Token Index: 831

Text #13

Max Range: 1.4035. Min Range: -1.4035

Max Act: 0.9697. Min Act: -0.0001

Data Index: 228536 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.0861. Min Act: -0.0001

Data Index: 1246456 (C4 (Web Text))

Max Activating Token Index: 24

Text #15

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.1063. Min Act: -0.0001

Data Index: 330992 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.0530. Min Act: -0.0001

Data Index: 545619 (C4 (Web Text))

Max Activating Token Index: 360

Text #17

Max Range: 1.4035. Min Range: -1.4035

Max Act: 1.0792. Min Act: -0.0001

Data Index: 403629 (C4 (Web Text))

Max Activating Token Index: 204

Text #18

Max Range: 1.4035. Min Range: -1.4035

Max Act: 0.9155. Min Act: -0.0001

Data Index: 447074 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.4035. Min Range: -1.4035

Max Act: 0.9749. Min Act: -0.0001

Data Index: 651183 (C4 (Web Text))

Max Activating Token Index: 204