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

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

Neuron 3349 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.6013. Min Range: -2.6013

Max Act: 2.5006. Min Act: -0.0000

Data Index: 268967 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 2.6013. Min Range: -2.6013

Max Act: 2.6013. Min Act: -0.0000

Data Index: 405343 (C4 (Web Text))

Max Activating Token Index: 754

Text #2

Max Range: 2.6013. Min Range: -2.6013

Max Act: 2.3317. Min Act: -0.0000

Data Index: 1144567 (C4 (Web Text))

Max Activating Token Index: 314

Text #3

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.9286. Min Act: -0.0000

Data Index: 940848 (C4 (Web Text))

Max Activating Token Index: 490

Text #4

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.8400. Min Act: -0.0000

Data Index: 1041783 (C4 (Web Text))

Max Activating Token Index: 457

Text #5

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.8376. Min Act: -0.0000

Data Index: 1290014 (C4 (Web Text))

Max Activating Token Index: 100

Text #6

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.6352. Min Act: -0.0000

Data Index: 184126 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.9268. Min Act: -0.0000

Data Index: 696764 (C4 (Web Text))

Max Activating Token Index: 44

Text #8

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.9169. Min Act: -0.0000

Data Index: 87199 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.7683. Min Act: -0.0000

Data Index: 16976 (C4 (Web Text))

Max Activating Token Index: 467

Text #10

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.6799. Min Act: -0.0000

Data Index: 938670 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.8657. Min Act: -0.0000

Data Index: 1165083 (C4 (Web Text))

Max Activating Token Index: 893

Text #12

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.6342. Min Act: -0.0000

Data Index: 809059 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.7012. Min Act: -0.0000

Data Index: 217137 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.7127. Min Act: -0.0000

Data Index: 564894 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.9153. Min Act: -0.0000

Data Index: 1235583 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.7029. Min Act: -0.0000

Data Index: 1329562 (C4 (Web Text))

Max Activating Token Index: 58

Text #17

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.5975. Min Act: -0.0000

Data Index: 95135 (C4 (Web Text))

Max Activating Token Index: 81

Text #18

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.5877. Min Act: -0.0000

Data Index: 1256622 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 2.6013. Min Range: -2.6013

Max Act: 1.5884. Min Act: -0.0000

Data Index: 291552 (C4 (Web Text))

Max Activating Token Index: 593