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

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

Neuron 564 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.8016. Min Act: -0.0000

Data Index: 356257 (C4 (Web Text))

Max Activating Token Index: 151

Text #1

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.7406. Min Act: -0.0000

Data Index: 863186 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6297. Min Act: -0.0000

Data Index: 1131270 (C4 (Web Text))

Max Activating Token Index: 210

Text #3

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6056. Min Act: -0.0000

Data Index: 441956 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6713. Min Act: -0.0000

Data Index: 856802 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5833. Min Act: -0.0000

Data Index: 82325 (C4 (Web Text))

Max Activating Token Index: 241

Text #6

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.6112. Min Act: -0.0000

Data Index: 751257 (C4 (Web Text))

Max Activating Token Index: 719

Text #7

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5699. Min Act: -0.0000

Data Index: 1306864 (C4 (Web Text))

Max Activating Token Index: 267

Text #8

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5481. Min Act: -0.0000

Data Index: 1044097 (C4 (Web Text))

Max Activating Token Index: 851

Text #9

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5424. Min Act: -0.0000

Data Index: 337249 (C4 (Web Text))

Max Activating Token Index: 763

Text #10

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5859. Min Act: -0.0000

Data Index: 240152 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5743. Min Act: -0.0000

Data Index: 882722 (C4 (Web Text))

Max Activating Token Index: 713

Text #12

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5416. Min Act: -0.0000

Data Index: 849698 (C4 (Web Text))

Max Activating Token Index: 278

Text #13

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5494. Min Act: -0.0000

Data Index: 1326617 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5316. Min Act: -0.0000

Data Index: 578739 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5299. Min Act: -0.0000

Data Index: 178294 (C4 (Web Text))

Max Activating Token Index: 300

Text #16

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5176. Min Act: -0.0000

Data Index: 951709 (C4 (Web Text))

Max Activating Token Index: 681

Text #17

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.5536. Min Act: -0.0000

Data Index: 957406 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.4892. Min Act: -0.0000

Data Index: 362644 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.8016. Min Range: -0.8016

Max Act: 0.3669. Min Act: -0.0000

Data Index: 1065504 (C4 (Web Text))

Max Activating Token Index: 242