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

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

Neuron 80 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.3789. Min Range: -4.3789

Max Act: 4.3789. Min Act: -0.0000

Data Index: 1003161 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 4.3789. Min Range: -4.3789

Max Act: 3.0567. Min Act: -0.0000

Data Index: 125436 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.6925. Min Act: -0.0000

Data Index: 1183740 (C4 (Web Text))

Max Activating Token Index: 190

Text #3

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.6394. Min Act: -0.0000

Data Index: 785438 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.7025. Min Act: -0.0000

Data Index: 754347 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.4480. Min Act: -0.0000

Data Index: 1017988 (C4 (Web Text))

Max Activating Token Index: 732

Text #6

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.5721. Min Act: -0.0000

Data Index: 374204 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.4686. Min Act: -0.0000

Data Index: 667790 (C4 (Web Text))

Max Activating Token Index: 976

Text #8

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.1302. Min Act: -0.0000

Data Index: 50526 (C4 (Web Text))

Max Activating Token Index: 916

Text #9

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.2036. Min Act: -0.0000

Data Index: 432869 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.2698. Min Act: -0.0000

Data Index: 709898 (C4 (Web Text))

Max Activating Token Index: 831

Text #11

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.2619. Min Act: -0.0000

Data Index: 984974 (C4 (Web Text))

Max Activating Token Index: 687

Text #12

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.1246. Min Act: -0.0000

Data Index: 879212 (C4 (Web Text))

Max Activating Token Index: 312

Text #13

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.2036. Min Act: -0.0000

Data Index: 1086278 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.1722. Min Act: -0.0000

Data Index: 4506 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.1175. Min Act: -0.0000

Data Index: 735483 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.1120. Min Act: -0.0000

Data Index: 696471 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.0341. Min Act: -0.0000

Data Index: 1127486 (C4 (Web Text))

Max Activating Token Index: 1000

Text #18

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.0155. Min Act: -0.0000

Data Index: 41469 (C4 (Web Text))

Max Activating Token Index: 78

Text #19

Max Range: 4.3789. Min Range: -4.3789

Max Act: 2.1137. Min Act: -0.0000

Data Index: 561928 (C4 (Web Text))

Max Activating Token Index: 749