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

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

Neuron 5102 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.5430. Min Act: -0.0000

Data Index: 867616 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.3797. Min Act: -0.0000

Data Index: 839009 (C4 (Web Text))

Max Activating Token Index: 289

Text #2

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.4516. Min Act: -0.0000

Data Index: 366837 (C4 (Web Text))

Max Activating Token Index: 706

Text #3

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.3102. Min Act: -0.0000

Data Index: 881788 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.2584. Min Act: -0.0000

Data Index: 226568 (C4 (Web Text))

Max Activating Token Index: 806

Text #5

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.1856. Min Act: -0.0000

Data Index: 1513709 (Python Code)

Max Activating Token Index: 823

Text #6

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.2022. Min Act: -0.0000

Data Index: 1352415 (C4 (Web Text))

Max Activating Token Index: 540

Text #7

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.2373. Min Act: -0.0000

Data Index: 159139 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.1479. Min Act: -0.0000

Data Index: 985392 (C4 (Web Text))

Max Activating Token Index: 829

Text #9

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0790. Min Act: -0.0000

Data Index: 1251155 (C4 (Web Text))

Max Activating Token Index: 244

Text #10

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0809. Min Act: -0.0000

Data Index: 557879 (C4 (Web Text))

Max Activating Token Index: 579

Text #11

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0918. Min Act: -0.0000

Data Index: 855413 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0315. Min Act: -0.0000

Data Index: 624590 (C4 (Web Text))

Max Activating Token Index: 760

Text #13

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0228. Min Act: -0.0000

Data Index: 1143313 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0806. Min Act: -0.0000

Data Index: 716801 (C4 (Web Text))

Max Activating Token Index: 738

Text #15

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0800. Min Act: -0.0000

Data Index: 104525 (C4 (Web Text))

Max Activating Token Index: 966

Text #16

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0740. Min Act: -0.0000

Data Index: 810730 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 1.5430. Min Range: -1.5430

Max Act: 1.0687. Min Act: -0.0000

Data Index: 129762 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 1.5430. Min Range: -1.5430

Max Act: 0.9687. Min Act: -0.0000

Data Index: 1605068 (Python Code)

Max Activating Token Index: 985

Text #19

Max Range: 1.5430. Min Range: -1.5430

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1258038 (C4 (Web Text))

Max Activating Token Index: 525