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

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

Neuron 3964 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.9598. Min Act: -0.0000

Data Index: 948667 (C4 (Web Text))

Max Activating Token Index: 553

Text #1

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8847. Min Act: -0.0000

Data Index: 548655 (C4 (Web Text))

Max Activating Token Index: 167

Text #2

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.8293. Min Act: -0.0000

Data Index: 590420 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7727. Min Act: -0.0000

Data Index: 843133 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7368. Min Act: -0.0000

Data Index: 831764 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7163. Min Act: -0.0000

Data Index: 583545 (C4 (Web Text))

Max Activating Token Index: 91

Text #6

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7023. Min Act: -0.0000

Data Index: 528587 (C4 (Web Text))

Max Activating Token Index: 46

Text #7

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6939. Min Act: -0.0000

Data Index: 119615 (C4 (Web Text))

Max Activating Token Index: 218

Text #8

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7084. Min Act: -0.0000

Data Index: 1270939 (C4 (Web Text))

Max Activating Token Index: 247

Text #9

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6952. Min Act: -0.0000

Data Index: 1067955 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6735. Min Act: -0.0000

Data Index: 1129382 (C4 (Web Text))

Max Activating Token Index: 421

Text #11

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6715. Min Act: -0.0000

Data Index: 280617 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.7036. Min Act: -0.0000

Data Index: 450474 (C4 (Web Text))

Max Activating Token Index: 301

Text #13

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6517. Min Act: -0.0000

Data Index: 755821 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6541. Min Act: -0.0000

Data Index: 148819 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6324. Min Act: -0.0000

Data Index: 1202112 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6132. Min Act: -0.0000

Data Index: 419227 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6027. Min Act: -0.0000

Data Index: 993728 (C4 (Web Text))

Max Activating Token Index: 80

Text #18

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.6201. Min Act: -0.0000

Data Index: 1186657 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.9598. Min Range: -0.9598

Max Act: 0.5899. Min Act: -0.0000

Data Index: 48197 (C4 (Web Text))

Max Activating Token Index: 125