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

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

Neuron 2931 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.6146. Min Act: -0.0000

Data Index: 278781 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.5204. Min Act: -0.0000

Data Index: 265091 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4748. Min Act: -0.0000

Data Index: 136807 (C4 (Web Text))

Max Activating Token Index: 870

Text #3

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4471. Min Act: -0.0000

Data Index: 423005 (C4 (Web Text))

Max Activating Token Index: 251

Text #4

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4559. Min Act: -0.0000

Data Index: 1431701 (Python Code)

Max Activating Token Index: 141

Text #5

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4280. Min Act: -0.0000

Data Index: 716296 (C4 (Web Text))

Max Activating Token Index: 155

Text #6

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4443. Min Act: -0.0000

Data Index: 1461667 (Python Code)

Max Activating Token Index: 405

Text #7

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4395. Min Act: -0.0000

Data Index: 389492 (C4 (Web Text))

Max Activating Token Index: 390

Text #8

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4378. Min Act: -0.0000

Data Index: 192278 (C4 (Web Text))

Max Activating Token Index: 811

Text #9

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4497. Min Act: -0.0000

Data Index: 1390520 (Python Code)

Max Activating Token Index: 305

Text #10

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4229. Min Act: -0.0000

Data Index: 1656674 (Python Code)

Max Activating Token Index: 437

Text #11

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4157. Min Act: -0.0000

Data Index: 1234349 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4142. Min Act: -0.0000

Data Index: 322458 (C4 (Web Text))

Max Activating Token Index: 349

Text #13

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4096. Min Act: -0.0000

Data Index: 241565 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4068. Min Act: -0.0000

Data Index: 1532535 (Python Code)

Max Activating Token Index: 767

Text #15

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.3791. Min Act: -0.0000

Data Index: 115039 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.4037. Min Act: -0.0000

Data Index: 305443 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.3853. Min Act: -0.0000

Data Index: 327646 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1008504 (C4 (Web Text))

Max Activating Token Index: 907

Text #19

Max Range: 0.6146. Min Range: -0.6146

Max Act: 0.3702. Min Act: -0.0000

Data Index: 172427 (C4 (Web Text))

Max Activating Token Index: 706