Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.1154. Min Act: -0.0002

Data Index: 58865 (C4 (Web Text))

Max Activating Token Index: 809

Text #1

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0789. Min Act: -0.0002

Data Index: 988207 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0751. Min Act: -0.0002

Data Index: 1029715 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0750. Min Act: -0.0002

Data Index: 839061 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0732. Min Act: -0.0002

Data Index: 146084 (C4 (Web Text))

Max Activating Token Index: 32

Text #5

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0693. Min Act: -0.0002

Data Index: 973043 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0700. Min Act: -0.0002

Data Index: 1083578 (C4 (Web Text))

Max Activating Token Index: 496

Text #7

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0657. Min Act: -0.0002

Data Index: 460231 (C4 (Web Text))

Max Activating Token Index: 368

Text #8

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0656. Min Act: -0.0002

Data Index: 1000332 (C4 (Web Text))

Max Activating Token Index: 748

Text #9

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0643. Min Act: -0.0002

Data Index: 792838 (C4 (Web Text))

Max Activating Token Index: 838

Text #10

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0619. Min Act: -0.0002

Data Index: 423619 (C4 (Web Text))

Max Activating Token Index: 157

Text #11

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0616. Min Act: -0.0002

Data Index: 124303 (C4 (Web Text))

Max Activating Token Index: 309

Text #12

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0593. Min Act: -0.0002

Data Index: 74335 (C4 (Web Text))

Max Activating Token Index: 403

Text #13

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0608. Min Act: -0.0002

Data Index: 760464 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0599. Min Act: -0.0002

Data Index: 572018 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0620. Min Act: -0.0002

Data Index: 1218736 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0623. Min Act: -0.0002

Data Index: 514914 (C4 (Web Text))

Max Activating Token Index: 535

Text #17

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0617. Min Act: -0.0002

Data Index: 154495 (C4 (Web Text))

Max Activating Token Index: 142

Text #18

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0588. Min Act: -0.0002

Data Index: 315323 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 0.1154. Min Range: -0.1154

Max Act: 0.0567. Min Act: -0.0002

Data Index: 1002875 (C4 (Web Text))

Max Activating Token Index: 827