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

Dataset: The Pile

Neuron 513 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: 5.8072. Min Range: -5.8072

Max Act: 5.8072. Min Act: -0.0000

Data Index: 564137 (The Pile)

Max Activating Token Index: 596

Text #1

Max Range: 5.8072. Min Range: -5.8072

Max Act: 4.6294. Min Act: -0.0000

Data Index: 352966 (The Pile)

Max Activating Token Index: 200

Text #2

Max Range: 5.8072. Min Range: -5.8072

Max Act: 4.1931. Min Act: -0.0000

Data Index: 943746 (The Pile)

Max Activating Token Index: 393

Text #3

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.7758. Min Act: -0.0000

Data Index: 1924665 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.9031. Min Act: -0.0000

Data Index: 1475847 (The Pile)

Max Activating Token Index: 102

Text #5

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.9730. Min Act: -0.0000

Data Index: 1527272 (The Pile)

Max Activating Token Index: 119

Text #6

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.7282. Min Act: -0.0000

Data Index: 1195171 (The Pile)

Max Activating Token Index: 762

Text #7

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.5434. Min Act: -0.0000

Data Index: 72477 (The Pile)

Max Activating Token Index: 45

Text #8

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.3935. Min Act: -0.0000

Data Index: 550461 (The Pile)

Max Activating Token Index: 334

Text #9

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.3132. Min Act: -0.0000

Data Index: 1265695 (The Pile)

Max Activating Token Index: 234

Text #10

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.1098. Min Act: -0.0000

Data Index: 1534383 (The Pile)

Max Activating Token Index: 515

Text #11

Max Range: 5.8072. Min Range: -5.8072

Max Act: 3.4917. Min Act: -0.0000

Data Index: 226650 (The Pile)

Max Activating Token Index: 544

Text #12

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.4572. Min Act: -0.0000

Data Index: 1701531 (The Pile)

Max Activating Token Index: 954

Text #13

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.8835. Min Act: -0.0000

Data Index: 1659674 (The Pile)

Max Activating Token Index: 316

Text #14

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.9270. Min Act: -0.0000

Data Index: 180359 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.9510. Min Act: -0.0000

Data Index: 723594 (The Pile)

Max Activating Token Index: 156

Text #16

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.9275. Min Act: -0.0000

Data Index: 810149 (The Pile)

Max Activating Token Index: 257

Text #17

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.8255. Min Act: -0.0000

Data Index: 764229 (The Pile)

Max Activating Token Index: 255

Text #18

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.8838. Min Act: -0.0000

Data Index: 759542 (The Pile)

Max Activating Token Index: 291

Text #19

Max Range: 5.8072. Min Range: -5.8072

Max Act: 2.8545. Min Act: -0.0000

Data Index: 1305647 (The Pile)

Max Activating Token Index: 186