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

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

Neuron 2415 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.3394. Min Act: -0.0000

Data Index: 646042 (C4 (Web Text))

Max Activating Token Index: 715

Text #1

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.3051. Min Act: -0.0000

Data Index: 711265 (C4 (Web Text))

Max Activating Token Index: 891

Text #2

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.3084. Min Act: -0.0000

Data Index: 230012 (C4 (Web Text))

Max Activating Token Index: 923

Text #3

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.3462. Min Act: -0.0000

Data Index: 150308 (C4 (Web Text))

Max Activating Token Index: 322

Text #4

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.2621. Min Act: -0.0000

Data Index: 991611 (C4 (Web Text))

Max Activating Token Index: 720

Text #5

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.2598. Min Act: -0.0000

Data Index: 735071 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1385. Min Act: -0.0000

Data Index: 592975 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1988. Min Act: -0.0000

Data Index: 678445 (C4 (Web Text))

Max Activating Token Index: 549

Text #8

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1659. Min Act: -0.0000

Data Index: 683157 (C4 (Web Text))

Max Activating Token Index: 556

Text #9

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1688. Min Act: -0.0000

Data Index: 399870 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.2242. Min Act: -0.0000

Data Index: 490497 (C4 (Web Text))

Max Activating Token Index: 851

Text #11

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1036. Min Act: -0.0000

Data Index: 241148 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0879. Min Act: -0.0000

Data Index: 125450 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0872. Min Act: -0.0000

Data Index: 1201861 (C4 (Web Text))

Max Activating Token Index: 471

Text #14

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0185. Min Act: -0.0000

Data Index: 848837 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0797. Min Act: -0.0000

Data Index: 533516 (C4 (Web Text))

Max Activating Token Index: 590

Text #16

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1321. Min Act: -0.0000

Data Index: 263848 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1254. Min Act: -0.0000

Data Index: 712679 (C4 (Web Text))

Max Activating Token Index: 610

Text #18

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.0525. Min Act: -0.0000

Data Index: 847954 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 1.3462. Min Range: -1.3462

Max Act: 1.1182. Min Act: -0.0000

Data Index: 187545 (C4 (Web Text))

Max Activating Token Index: 533