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

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

Neuron 3574 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: 2.2097. Min Range: -2.2097

Max Act: 2.2097. Min Act: -0.0000

Data Index: 1050041 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.7358. Min Act: -0.0000

Data Index: 464785 (C4 (Web Text))

Max Activating Token Index: 247

Text #2

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.5310. Min Act: -0.0000

Data Index: 1053634 (C4 (Web Text))

Max Activating Token Index: 337

Text #3

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.3861. Min Act: -0.0000

Data Index: 1050635 (C4 (Web Text))

Max Activating Token Index: 219

Text #4

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.4871. Min Act: -0.0000

Data Index: 37476 (C4 (Web Text))

Max Activating Token Index: 924

Text #5

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.2772. Min Act: -0.0000

Data Index: 1315569 (C4 (Web Text))

Max Activating Token Index: 760

Text #6

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.3297. Min Act: -0.0000

Data Index: 1260420 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.3133. Min Act: -0.0000

Data Index: 469586 (C4 (Web Text))

Max Activating Token Index: 547

Text #8

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.3535. Min Act: -0.0000

Data Index: 833556 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.2429. Min Act: -0.0000

Data Index: 474412 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.2016. Min Act: -0.0000

Data Index: 195433 (C4 (Web Text))

Max Activating Token Index: 505

Text #11

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.0977. Min Act: -0.0000

Data Index: 104846 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.1658. Min Act: -0.0000

Data Index: 228821 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.1673. Min Act: -0.0000

Data Index: 159471 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.0825. Min Act: -0.0000

Data Index: 249211 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.0851. Min Act: -0.0000

Data Index: 1012800 (C4 (Web Text))

Max Activating Token Index: 220

Text #16

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.0775. Min Act: -0.0000

Data Index: 397674 (C4 (Web Text))

Max Activating Token Index: 317

Text #17

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.0016. Min Act: -0.0000

Data Index: 1008074 (C4 (Web Text))

Max Activating Token Index: 691

Text #18

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.0203. Min Act: -0.0000

Data Index: 24671 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 2.2097. Min Range: -2.2097

Max Act: 1.0720. Min Act: -0.0000

Data Index: 707849 (C4 (Web Text))

Max Activating Token Index: 39