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

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

Neuron 5940 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1352. Min Range: -4.1352

Max Act: 4.1352. Min Act: -0.0000

Data Index: 1015896 (C4 (Web Text))

Max Activating Token Index: 958

Text #1

Max Range: 4.1352. Min Range: -4.1352

Max Act: 3.6337. Min Act: -0.0000

Data Index: 1086737 (C4 (Web Text))

Max Activating Token Index: 770

Text #2

Max Range: 4.1352. Min Range: -4.1352

Max Act: 3.4623. Min Act: -0.0000

Data Index: 215189 (C4 (Web Text))

Max Activating Token Index: 722

Text #3

Max Range: 4.1352. Min Range: -4.1352

Max Act: 3.4833. Min Act: -0.0000

Data Index: 405057 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 4.1352. Min Range: -4.1352

Max Act: 3.4310. Min Act: -0.0000

Data Index: 851095 (C4 (Web Text))

Max Activating Token Index: 635

Text #5

Max Range: 4.1352. Min Range: -4.1352

Max Act: 3.0800. Min Act: -0.0000

Data Index: 1001779 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.8480. Min Act: -0.0000

Data Index: 1558114 (Python Code)

Max Activating Token Index: 803

Text #7

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.6708. Min Act: -0.0000

Data Index: 1394793 (Python Code)

Max Activating Token Index: 945

Text #8

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.0805. Min Act: -0.0000

Data Index: 81529 (C4 (Web Text))

Max Activating Token Index: 266

Text #9

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.7111. Min Act: -0.0000

Data Index: 315187 (C4 (Web Text))

Max Activating Token Index: 1004

Text #10

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.4825. Min Act: -0.0000

Data Index: 1356342 (C4 (Web Text))

Max Activating Token Index: 449

Text #11

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.4745. Min Act: -0.0000

Data Index: 109591 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.4514. Min Act: -0.0000

Data Index: 1587167 (Python Code)

Max Activating Token Index: 449

Text #13

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.4421. Min Act: -0.0000

Data Index: 1546660 (Python Code)

Max Activating Token Index: 460

Text #14

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.1797. Min Act: -0.0000

Data Index: 154312 (C4 (Web Text))

Max Activating Token Index: 376

Text #15

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.5025. Min Act: -0.0000

Data Index: 1559455 (Python Code)

Max Activating Token Index: 378

Text #16

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.2628. Min Act: -0.0000

Data Index: 1444290 (Python Code)

Max Activating Token Index: 91

Text #17

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.2355. Min Act: -0.0000

Data Index: 231281 (C4 (Web Text))

Max Activating Token Index: 147

Text #18

Max Range: 4.1352. Min Range: -4.1352

Max Act: 2.2863. Min Act: -0.0000

Data Index: 1439127 (Python Code)

Max Activating Token Index: 188

Text #19

Max Range: 4.1352. Min Range: -4.1352

Max Act: 1.9994. Min Act: -0.0000

Data Index: 839265 (C4 (Web Text))

Max Activating Token Index: 834