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

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

Neuron 560 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: 0.2672. Min Range: -0.2672

Max Act: 0.2672. Min Act: -0.0000

Data Index: 669946 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2501. Min Act: -0.0000

Data Index: 185801 (C4 (Web Text))

Max Activating Token Index: 309

Text #2

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2292. Min Act: -0.0000

Data Index: 129022 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2016. Min Act: -0.0000

Data Index: 132859 (C4 (Web Text))

Max Activating Token Index: 433

Text #4

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2006. Min Act: -0.0000

Data Index: 1104430 (C4 (Web Text))

Max Activating Token Index: 904

Text #5

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.2006. Min Act: -0.0000

Data Index: 435018 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1882. Min Act: -0.0000

Data Index: 1269335 (C4 (Web Text))

Max Activating Token Index: 445

Text #7

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1995. Min Act: -0.0000

Data Index: 328884 (C4 (Web Text))

Max Activating Token Index: 377

Text #8

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1843. Min Act: -0.0000

Data Index: 187862 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1033994 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1778. Min Act: -0.0000

Data Index: 256873 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1595. Min Act: -0.0000

Data Index: 142939 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1739. Min Act: -0.0000

Data Index: 722245 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1710. Min Act: -0.0000

Data Index: 44870 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1844. Min Act: -0.0000

Data Index: 12541 (C4 (Web Text))

Max Activating Token Index: 444

Text #15

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1705. Min Act: -0.0000

Data Index: 18691 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1840. Min Act: -0.0000

Data Index: 143314 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1834. Min Act: -0.0000

Data Index: 219145 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1747. Min Act: -0.0000

Data Index: 164977 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 0.2672. Min Range: -0.2672

Max Act: 0.1742. Min Act: -0.0000

Data Index: 327545 (C4 (Web Text))

Max Activating Token Index: 961