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

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

Neuron 4898 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.3551. Min Range: -7.3551

Max Act: 7.3551. Min Act: -0.0000

Data Index: 71397 (C4 (Web Text))

Max Activating Token Index: 826

Text #1

Max Range: 7.3551. Min Range: -7.3551

Max Act: 7.1854. Min Act: -0.0000

Data Index: 969220 (C4 (Web Text))

Max Activating Token Index: 424

Text #2

Max Range: 7.3551. Min Range: -7.3551

Max Act: 7.1818. Min Act: -0.0000

Data Index: 929682 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 7.3551. Min Range: -7.3551

Max Act: 6.7737. Min Act: -0.0000

Data Index: 16542 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 7.3551. Min Range: -7.3551

Max Act: 6.5081. Min Act: -0.0000

Data Index: 521762 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 7.3551. Min Range: -7.3551

Max Act: 6.3193. Min Act: -0.0000

Data Index: 1024869 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.9477. Min Act: -0.0000

Data Index: 211128 (C4 (Web Text))

Max Activating Token Index: 254

Text #7

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.8579. Min Act: -0.0000

Data Index: 123877 (C4 (Web Text))

Max Activating Token Index: 1015

Text #8

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.7959. Min Act: -0.0000

Data Index: 199340 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.5384. Min Act: -0.0000

Data Index: 432335 (C4 (Web Text))

Max Activating Token Index: 775

Text #10

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.9066. Min Act: -0.0000

Data Index: 798210 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.8427. Min Act: -0.0000

Data Index: 366537 (C4 (Web Text))

Max Activating Token Index: 406

Text #12

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.6797. Min Act: -0.0000

Data Index: 709696 (C4 (Web Text))

Max Activating Token Index: 737

Text #13

Max Range: 7.3551. Min Range: -7.3551

Max Act: 6.1706. Min Act: -0.0000

Data Index: 635871 (C4 (Web Text))

Max Activating Token Index: 246

Text #14

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.7884. Min Act: -0.0000

Data Index: 51904 (C4 (Web Text))

Max Activating Token Index: 501

Text #15

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.8007. Min Act: -0.0000

Data Index: 445486 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.2747. Min Act: -0.0000

Data Index: 532750 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.4499. Min Act: -0.0000

Data Index: 396460 (C4 (Web Text))

Max Activating Token Index: 415

Text #18

Max Range: 7.3551. Min Range: -7.3551

Max Act: 6.1708. Min Act: -0.0000

Data Index: 611214 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 7.3551. Min Range: -7.3551

Max Act: 5.4227. Min Act: -0.0000

Data Index: 1309238 (C4 (Web Text))

Max Activating Token Index: 992