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

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

Neuron 3480 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: 1.9241. Min Range: -1.9241

Max Act: 1.9241. Min Act: -0.0000

Data Index: 1317624 (C4 (Web Text))

Max Activating Token Index: 97

Text #1

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.8010. Min Act: -0.0000

Data Index: 602481 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.6756. Min Act: -0.0000

Data Index: 767325 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.6828. Min Act: -0.0000

Data Index: 579677 (C4 (Web Text))

Max Activating Token Index: 865

Text #4

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.5112. Min Act: -0.0000

Data Index: 346007 (C4 (Web Text))

Max Activating Token Index: 537

Text #5

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.5169. Min Act: -0.0000

Data Index: 1085646 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3745. Min Act: -0.0000

Data Index: 1212197 (C4 (Web Text))

Max Activating Token Index: 666

Text #7

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.5929. Min Act: -0.0000

Data Index: 1100130 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.4095. Min Act: -0.0000

Data Index: 1275379 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.4069. Min Act: -0.0000

Data Index: 837169 (C4 (Web Text))

Max Activating Token Index: 840

Text #10

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3244. Min Act: -0.0000

Data Index: 472557 (C4 (Web Text))

Max Activating Token Index: 860

Text #11

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3663. Min Act: -0.0000

Data Index: 1024379 (C4 (Web Text))

Max Activating Token Index: 230

Text #12

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3224. Min Act: -0.0001

Data Index: 1075699 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.5089. Min Act: -0.0000

Data Index: 1301450 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3880. Min Act: -0.0000

Data Index: 549306 (C4 (Web Text))

Max Activating Token Index: 1010

Text #15

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.2743. Min Act: -0.0000

Data Index: 1085722 (C4 (Web Text))

Max Activating Token Index: 484

Text #16

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.4032. Min Act: -0.0000

Data Index: 113605 (C4 (Web Text))

Max Activating Token Index: 816

Text #17

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.3001. Min Act: -0.0000

Data Index: 1482731 (Python Code)

Max Activating Token Index: 909

Text #18

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.2705. Min Act: -0.0000

Data Index: 430700 (C4 (Web Text))

Max Activating Token Index: 181

Text #19

Max Range: 1.9241. Min Range: -1.9241

Max Act: 1.1812. Min Act: -0.0000

Data Index: 696709 (C4 (Web Text))

Max Activating Token Index: 362