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

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

Neuron 5288 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: 1.0217. Min Range: -1.0217

Max Act: 1.0217. Min Act: -0.0000

Data Index: 965440 (C4 (Web Text))

Max Activating Token Index: 709

Text #1

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.9785. Min Act: -0.0000

Data Index: 188837 (C4 (Web Text))

Max Activating Token Index: 67

Text #2

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8720. Min Act: -0.0000

Data Index: 796350 (C4 (Web Text))

Max Activating Token Index: 712

Text #3

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8513. Min Act: -0.0000

Data Index: 582095 (C4 (Web Text))

Max Activating Token Index: 615

Text #4

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7806. Min Act: -0.0000

Data Index: 265034 (C4 (Web Text))

Max Activating Token Index: 130

Text #5

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7351. Min Act: -0.0000

Data Index: 1143198 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.8027. Min Act: -0.0000

Data Index: 76820 (C4 (Web Text))

Max Activating Token Index: 1015

Text #7

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7830. Min Act: -0.0000

Data Index: 559129 (C4 (Web Text))

Max Activating Token Index: 112

Text #8

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7734. Min Act: -0.0000

Data Index: 1033522 (C4 (Web Text))

Max Activating Token Index: 60

Text #9

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7462. Min Act: -0.0000

Data Index: 1240805 (C4 (Web Text))

Max Activating Token Index: 5

Text #10

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7456. Min Act: -0.0000

Data Index: 883000 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7010. Min Act: -0.0000

Data Index: 550212 (C4 (Web Text))

Max Activating Token Index: 853

Text #12

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7479. Min Act: -0.0000

Data Index: 1146391 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.6901. Min Act: -0.0000

Data Index: 839642 (C4 (Web Text))

Max Activating Token Index: 894

Text #14

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.6324. Min Act: -0.0000

Data Index: 255726 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.7086. Min Act: -0.0000

Data Index: 521346 (C4 (Web Text))

Max Activating Token Index: 79

Text #16

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.6831. Min Act: -0.0000

Data Index: 747267 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.6432. Min Act: -0.0000

Data Index: 255097 (C4 (Web Text))

Max Activating Token Index: 228

Text #18

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1160852 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 1.0217. Min Range: -1.0217

Max Act: 0.6730. Min Act: -0.0000

Data Index: 563320 (C4 (Web Text))

Max Activating Token Index: 260