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

Dataset: The Pile

Neuron 1780 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: 1.8545. Min Range: -1.8545

Max Act: 1.8249. Min Act: -0.0000

Data Index: 1864327 (The Pile)

Max Activating Token Index: 585

Text #1

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7597. Min Act: -0.0000

Data Index: 960183 (The Pile)

Max Activating Token Index: 11

Text #2

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7873. Min Act: -0.0000

Data Index: 1342146 (The Pile)

Max Activating Token Index: 119

Text #3

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7520. Min Act: -0.0000

Data Index: 1306980 (The Pile)

Max Activating Token Index: 635

Text #4

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8545. Min Act: -0.0000

Data Index: 22589 (The Pile)

Max Activating Token Index: 411

Text #5

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7035. Min Act: -0.0000

Data Index: 178815 (The Pile)

Max Activating Token Index: 184

Text #6

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7929. Min Act: -0.0000

Data Index: 1721612 (The Pile)

Max Activating Token Index: 357

Text #7

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.7185. Min Act: -0.0000

Data Index: 1194347 (The Pile)

Max Activating Token Index: 247

Text #8

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.6024. Min Act: -0.0000

Data Index: 906435 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.5891. Min Act: -0.0000

Data Index: 1897670 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.6740. Min Act: -0.0000

Data Index: 1481625 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.8253. Min Act: -0.0000

Data Index: 542428 (The Pile)

Max Activating Token Index: 804

Text #12

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.6601. Min Act: -0.0000

Data Index: 1006342 (The Pile)

Max Activating Token Index: 375

Text #13

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.5876. Min Act: -0.0000

Data Index: 535236 (The Pile)

Max Activating Token Index: 356

Text #14

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.6072. Min Act: -0.0000

Data Index: 1195421 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.5868. Min Act: -0.0000

Data Index: 1875594 (The Pile)

Max Activating Token Index: 536

Text #16

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.5935. Min Act: -0.0000

Data Index: 25290 (The Pile)

Max Activating Token Index: 356

Text #17

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.5944. Min Act: -0.0000

Data Index: 723248 (The Pile)

Max Activating Token Index: 548

Text #18

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.5959. Min Act: -0.0000

Data Index: 741789 (The Pile)

Max Activating Token Index: 557

Text #19

Max Range: 1.8545. Min Range: -1.8545

Max Act: 1.5003. Min Act: -0.0000

Data Index: 1506063 (The Pile)

Max Activating Token Index: 1002