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

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

Neuron 4990 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: 0.8759. Min Range: -0.8759

Max Act: 0.8759. Min Act: -0.0000

Data Index: 1477371 (Python Code)

Max Activating Token Index: 287

Text #1

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.8326. Min Act: -0.0000

Data Index: 1499714 (Python Code)

Max Activating Token Index: 547

Text #2

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.7970. Min Act: -0.0000

Data Index: 1543248 (Python Code)

Max Activating Token Index: 706

Text #3

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.7627. Min Act: -0.0000

Data Index: 1486401 (Python Code)

Max Activating Token Index: 627

Text #4

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.7723. Min Act: -0.0000

Data Index: 1572047 (Python Code)

Max Activating Token Index: 162

Text #5

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6519. Min Act: -0.0000

Data Index: 147079 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6070. Min Act: -0.0000

Data Index: 1071273 (C4 (Web Text))

Max Activating Token Index: 234

Text #7

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6228. Min Act: -0.0000

Data Index: 1594978 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6788. Min Act: -0.0000

Data Index: 1467065 (Python Code)

Max Activating Token Index: 347

Text #9

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6027. Min Act: -0.0000

Data Index: 747555 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6343. Min Act: -0.0000

Data Index: 912629 (C4 (Web Text))

Max Activating Token Index: 188

Text #11

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6495. Min Act: -0.0000

Data Index: 517540 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1582016 (Python Code)

Max Activating Token Index: 496

Text #13

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.5175. Min Act: -0.0000

Data Index: 1221061 (C4 (Web Text))

Max Activating Token Index: 923

Text #14

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.6097. Min Act: -0.0000

Data Index: 1431513 (Python Code)

Max Activating Token Index: 159

Text #15

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1403506 (Python Code)

Max Activating Token Index: 170

Text #16

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1564124 (Python Code)

Max Activating Token Index: 454

Text #17

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.5515. Min Act: -0.0000

Data Index: 1014694 (C4 (Web Text))

Max Activating Token Index: 207

Text #18

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1552038 (Python Code)

Max Activating Token Index: 332

Text #19

Max Range: 0.8759. Min Range: -0.8759

Max Act: 0.5493. Min Act: -0.0000

Data Index: 928067 (C4 (Web Text))

Max Activating Token Index: 947