Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1099 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3737. Min Act: -0.0003

Data Index: 431081 (C4 (Web Text))

Max Activating Token Index: 62

Text #1

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.3199. Min Act: -0.0003

Data Index: 886650 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2247. Min Act: -0.0003

Data Index: 485881 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2018. Min Act: -0.0003

Data Index: 1295562 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.2011. Min Act: -0.0002

Data Index: 68322 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1934. Min Act: -0.0003

Data Index: 164334 (C4 (Web Text))

Max Activating Token Index: 386

Text #6

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1924. Min Act: -0.0003

Data Index: 971180 (C4 (Web Text))

Max Activating Token Index: 667

Text #7

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1708. Min Act: -0.0002

Data Index: 1614735 (Python Code)

Max Activating Token Index: 308

Text #8

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1773. Min Act: -0.0003

Data Index: 1283705 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1801. Min Act: -0.0003

Data Index: 1061585 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1789. Min Act: -0.0003

Data Index: 1275283 (C4 (Web Text))

Max Activating Token Index: 321

Text #11

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1785. Min Act: -0.0003

Data Index: 1288371 (C4 (Web Text))

Max Activating Token Index: 672

Text #12

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1785. Min Act: -0.0003

Data Index: 1227009 (C4 (Web Text))

Max Activating Token Index: 65

Text #13

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1755. Min Act: -0.0003

Data Index: 344036 (C4 (Web Text))

Max Activating Token Index: 141

Text #14

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1718. Min Act: -0.0003

Data Index: 238831 (C4 (Web Text))

Max Activating Token Index: 14

Text #15

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1711. Min Act: -0.0003

Data Index: 290560 (C4 (Web Text))

Max Activating Token Index: 184

Text #16

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1673. Min Act: -0.0002

Data Index: 737557 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1666. Min Act: -0.0003

Data Index: 881494 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1644. Min Act: -0.0002

Data Index: 1460980 (Python Code)

Max Activating Token Index: 67

Text #19

Max Range: 0.3737. Min Range: -0.3737

Max Act: 0.1690. Min Act: -0.0003

Data Index: 1311175 (C4 (Web Text))

Max Activating Token Index: 281