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

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

Neuron 1326 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5046. Min Range: -2.5046

Max Act: 2.5046. Min Act: -0.0000

Data Index: 430923 (C4 (Web Text))

Max Activating Token Index: 402

Text #1

Max Range: 2.5046. Min Range: -2.5046

Max Act: 2.0555. Min Act: -0.0000

Data Index: 582185 (C4 (Web Text))

Max Activating Token Index: 669

Text #2

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.9122. Min Act: -0.0000

Data Index: 906211 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.8692. Min Act: -0.0000

Data Index: 977483 (C4 (Web Text))

Max Activating Token Index: 405

Text #4

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.8096. Min Act: -0.0000

Data Index: 680185 (C4 (Web Text))

Max Activating Token Index: 579

Text #5

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.8024. Min Act: -0.0000

Data Index: 239517 (C4 (Web Text))

Max Activating Token Index: 385

Text #6

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.7384. Min Act: -0.0000

Data Index: 128864 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.6358. Min Act: -0.0000

Data Index: 134075 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.7527. Min Act: -0.0000

Data Index: 464516 (C4 (Web Text))

Max Activating Token Index: 943

Text #9

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.7471. Min Act: -0.0000

Data Index: 1045180 (C4 (Web Text))

Max Activating Token Index: 704

Text #10

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.6212. Min Act: -0.0000

Data Index: 884566 (C4 (Web Text))

Max Activating Token Index: 243

Text #11

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.6747. Min Act: -0.0000

Data Index: 449509 (C4 (Web Text))

Max Activating Token Index: 130

Text #12

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.5850. Min Act: -0.0000

Data Index: 17913 (C4 (Web Text))

Max Activating Token Index: 14

Text #13

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.6091. Min Act: -0.0000

Data Index: 934951 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.6021. Min Act: -0.0000

Data Index: 1000894 (C4 (Web Text))

Max Activating Token Index: 662

Text #15

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.6397. Min Act: -0.0000

Data Index: 282889 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.5584. Min Act: -0.0000

Data Index: 610280 (C4 (Web Text))

Max Activating Token Index: 195

Text #17

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.5594. Min Act: -0.0000

Data Index: 102962 (C4 (Web Text))

Max Activating Token Index: 61

Text #18

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.5472. Min Act: -0.0000

Data Index: 1175797 (C4 (Web Text))

Max Activating Token Index: 990

Text #19

Max Range: 2.5046. Min Range: -2.5046

Max Act: 1.5825. Min Act: -0.0000

Data Index: 1090439 (C4 (Web Text))

Max Activating Token Index: 534