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

Dataset: The Pile

Neuron 2095 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.9613. Min Act: -0.0000

Data Index: 1517217 (The Pile)

Max Activating Token Index: 188

Text #1

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.9541. Min Act: -0.0000

Data Index: 95823 (The Pile)

Max Activating Token Index: 389

Text #2

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.9263. Min Act: -0.0000

Data Index: 648601 (The Pile)

Max Activating Token Index: 213

Text #3

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7966. Min Act: -0.0000

Data Index: 1814461 (The Pile)

Max Activating Token Index: 85

Text #4

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.8015. Min Act: -0.0000

Data Index: 965395 (The Pile)

Max Activating Token Index: 439

Text #5

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7729. Min Act: -0.0000

Data Index: 1523405 (The Pile)

Max Activating Token Index: 188

Text #6

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7519. Min Act: -0.0000

Data Index: 1990725 (The Pile)

Max Activating Token Index: 836

Text #7

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7584. Min Act: -0.0000

Data Index: 1074203 (The Pile)

Max Activating Token Index: 64

Text #8

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7611. Min Act: -0.0000

Data Index: 260436 (The Pile)

Max Activating Token Index: 552

Text #9

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.6585. Min Act: -0.0000

Data Index: 1153065 (The Pile)

Max Activating Token Index: 786

Text #10

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7159. Min Act: -0.0000

Data Index: 772303 (The Pile)

Max Activating Token Index: 702

Text #11

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7344. Min Act: -0.0000

Data Index: 1729803 (The Pile)

Max Activating Token Index: 472

Text #12

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7397. Min Act: -0.0000

Data Index: 1460957 (The Pile)

Max Activating Token Index: 179

Text #13

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7237. Min Act: -0.0000

Data Index: 886543 (The Pile)

Max Activating Token Index: 628

Text #14

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7095. Min Act: -0.0000

Data Index: 765899 (The Pile)

Max Activating Token Index: 178

Text #15

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7056. Min Act: -0.0000

Data Index: 1004258 (The Pile)

Max Activating Token Index: 913

Text #16

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.7033. Min Act: -0.0000

Data Index: 1971707 (The Pile)

Max Activating Token Index: 418

Text #17

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.6052. Min Act: -0.0000

Data Index: 1172700 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.6002. Min Act: -0.0000

Data Index: 1352228 (The Pile)

Max Activating Token Index: 344

Text #19

Max Range: 1.9613. Min Range: -1.9613

Max Act: 1.5947. Min Act: -0.0000

Data Index: 1825594 (The Pile)

Max Activating Token Index: 202