Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2543 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.6804. Min Act: -0.0000

Data Index: 473836 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.4729. Min Act: -0.0000

Data Index: 959799 (C4 (Web Text))

Max Activating Token Index: 9

Text #2

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3885. Min Act: -0.0000

Data Index: 121238 (C4 (Web Text))

Max Activating Token Index: 525

Text #3

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3008. Min Act: -0.0000

Data Index: 698239 (C4 (Web Text))

Max Activating Token Index: 125

Text #4

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3565. Min Act: -0.0000

Data Index: 1071852 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3929. Min Act: -0.0000

Data Index: 771038 (C4 (Web Text))

Max Activating Token Index: 792

Text #6

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.3114. Min Act: -0.0000

Data Index: 111508 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2568. Min Act: -0.0000

Data Index: 192897 (C4 (Web Text))

Max Activating Token Index: 615

Text #8

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2173. Min Act: -0.0000

Data Index: 470955 (C4 (Web Text))

Max Activating Token Index: 764

Text #9

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2080. Min Act: -0.0000

Data Index: 312708 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2308. Min Act: -0.0000

Data Index: 891214 (C4 (Web Text))

Max Activating Token Index: 638

Text #11

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.1955. Min Act: -0.0000

Data Index: 1599411 (Python Code)

Max Activating Token Index: 344

Text #12

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.1929. Min Act: -0.0000

Data Index: 50182 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.1788. Min Act: -0.0000

Data Index: 1262077 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2393. Min Act: -0.0000

Data Index: 711063 (C4 (Web Text))

Max Activating Token Index: 843

Text #15

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.2239. Min Act: -0.0000

Data Index: 593127 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.1187. Min Act: -0.0001

Data Index: 40321 (C4 (Web Text))

Max Activating Token Index: 983

Text #17

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.1430. Min Act: -0.0000

Data Index: 228142 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.1406. Min Act: -0.0000

Data Index: 688239 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 1.6804. Min Range: -1.6804

Max Act: 1.1355. Min Act: -0.0000

Data Index: 703218 (C4 (Web Text))

Max Activating Token Index: 124