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

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

Neuron 2716 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1232504 (C4 (Web Text))

Max Activating Token Index: 102

Text #1

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5378. Min Act: -0.0000

Data Index: 639857 (C4 (Web Text))

Max Activating Token Index: 441

Text #2

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5154. Min Act: -0.0000

Data Index: 631106 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5461. Min Act: -0.0000

Data Index: 992877 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5251. Min Act: -0.0000

Data Index: 254805 (C4 (Web Text))

Max Activating Token Index: 878

Text #5

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5725. Min Act: 0.0000

Data Index: 1333802 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5488. Min Act: -0.0000

Data Index: 1024678 (C4 (Web Text))

Max Activating Token Index: 195

Text #7

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1313605 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4941. Min Act: -0.0000

Data Index: 855659 (C4 (Web Text))

Max Activating Token Index: 978

Text #9

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4675. Min Act: -0.0000

Data Index: 483588 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5075. Min Act: -0.0000

Data Index: 372378 (C4 (Web Text))

Max Activating Token Index: 110

Text #11

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4847. Min Act: -0.0000

Data Index: 934078 (C4 (Web Text))

Max Activating Token Index: 621

Text #12

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4735. Min Act: -0.0000

Data Index: 224509 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4591. Min Act: -0.0000

Data Index: 42165 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5008. Min Act: -0.0000

Data Index: 665708 (C4 (Web Text))

Max Activating Token Index: 405

Text #15

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4691. Min Act: -0.0000

Data Index: 150407 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4344. Min Act: -0.0000

Data Index: 291458 (C4 (Web Text))

Max Activating Token Index: 615

Text #17

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4454. Min Act: 0.0001

Data Index: 345944 (C4 (Web Text))

Max Activating Token Index: 482

Text #18

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.5051. Min Act: -0.0000

Data Index: 225354 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 0.5725. Min Range: -0.5725

Max Act: 0.4557. Min Act: -0.0000

Data Index: 39317 (C4 (Web Text))

Max Activating Token Index: 850