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

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

Neuron 3145 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: 1.5393. Min Range: -1.5393

Max Act: 1.5393. Min Act: 0.0000

Data Index: 276071 (C4 (Web Text))

Max Activating Token Index: 462

Text #1

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.4426. Min Act: -0.0000

Data Index: 801393 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3944. Min Act: -0.0000

Data Index: 349415 (C4 (Web Text))

Max Activating Token Index: 601

Text #3

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3634. Min Act: -0.0000

Data Index: 936465 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3418. Min Act: -0.0000

Data Index: 936868 (C4 (Web Text))

Max Activating Token Index: 101

Text #5

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3072. Min Act: -0.0000

Data Index: 272376 (C4 (Web Text))

Max Activating Token Index: 312

Text #6

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3082. Min Act: -0.0000

Data Index: 681090 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3679. Min Act: -0.0000

Data Index: 1358666 (C4 (Web Text))

Max Activating Token Index: 670

Text #8

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.3599. Min Act: -0.0000

Data Index: 636012 (C4 (Web Text))

Max Activating Token Index: 865

Text #9

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1357217 (C4 (Web Text))

Max Activating Token Index: 241

Text #10

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2528. Min Act: -0.0000

Data Index: 752829 (C4 (Web Text))

Max Activating Token Index: 487

Text #11

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2321. Min Act: -0.0000

Data Index: 1043781 (C4 (Web Text))

Max Activating Token Index: 647

Text #12

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1939. Min Act: -0.0000

Data Index: 175112 (C4 (Web Text))

Max Activating Token Index: 292

Text #13

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.2899. Min Act: -0.0000

Data Index: 811344 (C4 (Web Text))

Max Activating Token Index: 659

Text #14

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1834. Min Act: -0.0000

Data Index: 1073260 (C4 (Web Text))

Max Activating Token Index: 666

Text #15

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1754. Min Act: -0.0000

Data Index: 1038327 (C4 (Web Text))

Max Activating Token Index: 69

Text #16

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1345. Min Act: -0.0000

Data Index: 1162102 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1593. Min Act: -0.0000

Data Index: 799258 (C4 (Web Text))

Max Activating Token Index: 384

Text #18

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1994. Min Act: -0.0000

Data Index: 116619 (C4 (Web Text))

Max Activating Token Index: 466

Text #19

Max Range: 1.5393. Min Range: -1.5393

Max Act: 1.1624. Min Act: -0.0000

Data Index: 658731 (C4 (Web Text))

Max Activating Token Index: 988