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

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

Neuron 4110 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.5645. Min Act: -0.0000

Data Index: 296331 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.4610. Min Act: -0.0000

Data Index: 391597 (C4 (Web Text))

Max Activating Token Index: 732

Text #2

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.3161. Min Act: -0.0000

Data Index: 1324761 (C4 (Web Text))

Max Activating Token Index: 648

Text #3

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.3554. Min Act: -0.0000

Data Index: 369084 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.3137. Min Act: -0.0000

Data Index: 38635 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.2779. Min Act: -0.0000

Data Index: 10733 (C4 (Web Text))

Max Activating Token Index: 266

Text #6

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1156572 (C4 (Web Text))

Max Activating Token Index: 434

Text #7

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.2550. Min Act: -0.0000

Data Index: 525082 (C4 (Web Text))

Max Activating Token Index: 280

Text #8

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.2463. Min Act: -0.0000

Data Index: 665357 (C4 (Web Text))

Max Activating Token Index: 369

Text #9

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.1753. Min Act: -0.0000

Data Index: 656618 (C4 (Web Text))

Max Activating Token Index: 445

Text #10

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.1753. Min Act: -0.0000

Data Index: 1027856 (C4 (Web Text))

Max Activating Token Index: 341

Text #11

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.0819. Min Act: -0.0000

Data Index: 299343 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.1425. Min Act: -0.0000

Data Index: 976173 (C4 (Web Text))

Max Activating Token Index: 716

Text #13

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.1052. Min Act: -0.0000

Data Index: 666322 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.0867. Min Act: -0.0000

Data Index: 156830 (C4 (Web Text))

Max Activating Token Index: 638

Text #15

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.0655. Min Act: -0.0000

Data Index: 145564 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.0588. Min Act: -0.0000

Data Index: 657576 (C4 (Web Text))

Max Activating Token Index: 177

Text #17

Max Range: 1.5645. Min Range: -1.5645

Max Act: 0.9760. Min Act: -0.0000

Data Index: 1353899 (C4 (Web Text))

Max Activating Token Index: 663

Text #18

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.1123. Min Act: -0.0000

Data Index: 431543 (C4 (Web Text))

Max Activating Token Index: 659

Text #19

Max Range: 1.5645. Min Range: -1.5645

Max Act: 1.0199. Min Act: -0.0000

Data Index: 1258268 (C4 (Web Text))

Max Activating Token Index: 163