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

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

Neuron 3591 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9563. Min Act: -0.0001

Data Index: 788614 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7403. Min Act: -0.0001

Data Index: 1274492 (C4 (Web Text))

Max Activating Token Index: 766

Text #2

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9309. Min Act: -0.0001

Data Index: 353989 (C4 (Web Text))

Max Activating Token Index: 154

Text #3

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8587. Min Act: -0.0001

Data Index: 1196660 (C4 (Web Text))

Max Activating Token Index: 137

Text #4

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.9012. Min Act: -0.0001

Data Index: 745551 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7995. Min Act: -0.0001

Data Index: 1106558 (C4 (Web Text))

Max Activating Token Index: 128

Text #6

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7918. Min Act: -0.0001

Data Index: 597601 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7728. Min Act: -0.0001

Data Index: 531292 (C4 (Web Text))

Max Activating Token Index: 165

Text #8

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.8642. Min Act: -0.0001

Data Index: 128050 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6515. Min Act: -0.0001

Data Index: 305147 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6952. Min Act: -0.0001

Data Index: 109590 (C4 (Web Text))

Max Activating Token Index: 161

Text #11

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7102. Min Act: -0.0001

Data Index: 1207385 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7028. Min Act: -0.0001

Data Index: 621049 (C4 (Web Text))

Max Activating Token Index: 269

Text #13

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7497. Min Act: -0.0001

Data Index: 958225 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6567. Min Act: -0.0001

Data Index: 559137 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6995. Min Act: -0.0001

Data Index: 464390 (C4 (Web Text))

Max Activating Token Index: 100

Text #16

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6384. Min Act: -0.0001

Data Index: 150532 (C4 (Web Text))

Max Activating Token Index: 137

Text #17

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.7009. Min Act: -0.0001

Data Index: 389922 (C4 (Web Text))

Max Activating Token Index: 54

Text #18

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6925. Min Act: -0.0001

Data Index: 823691 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.9563. Min Range: -0.9563

Max Act: 0.6138. Min Act: -0.0001

Data Index: 254592 (C4 (Web Text))

Max Activating Token Index: 304