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

Dataset: The Pile

Neuron 3653 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7933. Min Act: -0.0000

Data Index: 966702 (The Pile)

Max Activating Token Index: 950

Text #1

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.9283. Min Act: -0.0000

Data Index: 1238900 (The Pile)

Max Activating Token Index: 595

Text #2

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8682. Min Act: -0.0000

Data Index: 790867 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7234. Min Act: -0.0000

Data Index: 1018487 (The Pile)

Max Activating Token Index: 837

Text #4

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.9032. Min Act: -0.0000

Data Index: 288372 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.9151. Min Act: -0.0000

Data Index: 624927 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8516. Min Act: -0.0000

Data Index: 805595 (The Pile)

Max Activating Token Index: 376

Text #7

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7564. Min Act: -0.0000

Data Index: 1983282 (The Pile)

Max Activating Token Index: 615

Text #8

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7785. Min Act: -0.0000

Data Index: 1656853 (The Pile)

Max Activating Token Index: 739

Text #9

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.6540. Min Act: -0.0000

Data Index: 870752 (The Pile)

Max Activating Token Index: 808

Text #10

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7908. Min Act: -0.0000

Data Index: 1463665 (The Pile)

Max Activating Token Index: 621

Text #11

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.8574. Min Act: -0.0000

Data Index: 671552 (The Pile)

Max Activating Token Index: 960

Text #12

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.6029. Min Act: -0.0000

Data Index: 772585 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.5861. Min Act: -0.0000

Data Index: 1363315 (The Pile)

Max Activating Token Index: 529

Text #14

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7626. Min Act: -0.0000

Data Index: 1640082 (The Pile)

Max Activating Token Index: 455

Text #15

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.6842. Min Act: -0.0000

Data Index: 992261 (The Pile)

Max Activating Token Index: 295

Text #16

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.7774. Min Act: -0.0000

Data Index: 317785 (The Pile)

Max Activating Token Index: 193

Text #17

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.5872. Min Act: -0.0000

Data Index: 388730 (The Pile)

Max Activating Token Index: 15

Text #18

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.5788. Min Act: -0.0000

Data Index: 2187 (The Pile)

Max Activating Token Index: 781

Text #19

Max Range: 1.9283. Min Range: -1.9283

Max Act: 1.5608. Min Act: -0.0000

Data Index: 1030210 (The Pile)

Max Activating Token Index: 560