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

Dataset: The Pile

Neuron 408 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.3080. Min Act: -0.0000

Data Index: 374176 (The Pile)

Max Activating Token Index: 739

Text #1

Max Range: 1.3080. Min Range: -1.3080

Max Act: 1.1552. Min Act: -0.0000

Data Index: 1255420 (The Pile)

Max Activating Token Index: 283

Text #2

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9845. Min Act: -0.0000

Data Index: 1130412 (The Pile)

Max Activating Token Index: 633

Text #3

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9087. Min Act: -0.0000

Data Index: 1720217 (The Pile)

Max Activating Token Index: 604

Text #4

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9570. Min Act: -0.0000

Data Index: 1615025 (The Pile)

Max Activating Token Index: 814

Text #5

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8414. Min Act: -0.0000

Data Index: 564488 (The Pile)

Max Activating Token Index: 792

Text #6

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9101. Min Act: -0.0000

Data Index: 821314 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.9483. Min Act: -0.0000

Data Index: 1065148 (The Pile)

Max Activating Token Index: 789

Text #8

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1847994 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7856. Min Act: -0.0000

Data Index: 633273 (The Pile)

Max Activating Token Index: 502

Text #10

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8676. Min Act: -0.0000

Data Index: 241632 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8418. Min Act: -0.0000

Data Index: 1502415 (The Pile)

Max Activating Token Index: 406

Text #12

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8343. Min Act: -0.0000

Data Index: 40350 (The Pile)

Max Activating Token Index: 463

Text #13

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8053. Min Act: -0.0000

Data Index: 765314 (The Pile)

Max Activating Token Index: 562

Text #14

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7705. Min Act: -0.0000

Data Index: 1060939 (The Pile)

Max Activating Token Index: 609

Text #15

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8262. Min Act: -0.0000

Data Index: 499594 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7127. Min Act: -0.0000

Data Index: 1406547 (The Pile)

Max Activating Token Index: 545

Text #17

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1814792 (The Pile)

Max Activating Token Index: 246

Text #18

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1889713 (The Pile)

Max Activating Token Index: 80

Text #19

Max Range: 1.3080. Min Range: -1.3080

Max Act: 0.7700. Min Act: -0.0000

Data Index: 740631 (The Pile)

Max Activating Token Index: 809