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

Dataset: The Pile

Neuron 3769 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4283. Min Range: -3.4283

Max Act: 3.4283. Min Act: -0.0000

Data Index: 1682743 (The Pile)

Max Activating Token Index: 24

Text #1

Max Range: 3.4283. Min Range: -3.4283

Max Act: 3.2761. Min Act: -0.0000

Data Index: 1708474 (The Pile)

Max Activating Token Index: 293

Text #2

Max Range: 3.4283. Min Range: -3.4283

Max Act: 3.1984. Min Act: -0.0000

Data Index: 727155 (The Pile)

Max Activating Token Index: 258

Text #3

Max Range: 3.4283. Min Range: -3.4283

Max Act: 3.1516. Min Act: -0.0000

Data Index: 843102 (The Pile)

Max Activating Token Index: 674

Text #4

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.9998. Min Act: -0.0000

Data Index: 525494 (The Pile)

Max Activating Token Index: 650

Text #5

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.6702. Min Act: -0.0000

Data Index: 1031515 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.9326. Min Act: -0.0000

Data Index: 511411 (The Pile)

Max Activating Token Index: 473

Text #7

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.6614. Min Act: -0.0000

Data Index: 117711 (The Pile)

Max Activating Token Index: 169

Text #8

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.7755. Min Act: -0.0000

Data Index: 1676464 (The Pile)

Max Activating Token Index: 251

Text #9

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.4929. Min Act: -0.0000

Data Index: 1520625 (The Pile)

Max Activating Token Index: 739

Text #10

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.4118. Min Act: -0.0000

Data Index: 603728 (The Pile)

Max Activating Token Index: 233

Text #11

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.5959. Min Act: -0.0000

Data Index: 1967530 (The Pile)

Max Activating Token Index: 113

Text #12

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.4496. Min Act: -0.0000

Data Index: 373593 (The Pile)

Max Activating Token Index: 291

Text #13

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.4387. Min Act: -0.0000

Data Index: 384440 (The Pile)

Max Activating Token Index: 526

Text #14

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.3326. Min Act: -0.0000

Data Index: 1696659 (The Pile)

Max Activating Token Index: 237

Text #15

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.5892. Min Act: -0.0000

Data Index: 786172 (The Pile)

Max Activating Token Index: 231

Text #16

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.5709. Min Act: -0.0000

Data Index: 1687108 (The Pile)

Max Activating Token Index: 768

Text #17

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.4017. Min Act: -0.0000

Data Index: 978449 (The Pile)

Max Activating Token Index: 524

Text #18

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.5549. Min Act: -0.0000

Data Index: 766375 (The Pile)

Max Activating Token Index: 863

Text #19

Max Range: 3.4283. Min Range: -3.4283

Max Act: 2.5032. Min Act: -0.0000

Data Index: 527525 (The Pile)

Max Activating Token Index: 315