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

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

Neuron 3319 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1898. Min Act: -0.0000

Data Index: 215022 (C4 (Web Text))

Max Activating Token Index: 895

Text #1

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1458351 (Python Code)

Max Activating Token Index: 646

Text #2

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0887. Min Act: -0.0001

Data Index: 1603593 (Python Code)

Max Activating Token Index: 550

Text #3

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0998. Min Act: -0.0001

Data Index: 1379438 (Python Code)

Max Activating Token Index: 735

Text #4

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0907. Min Act: -0.0000

Data Index: 519502 (C4 (Web Text))

Max Activating Token Index: 265

Text #5

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0834. Min Act: -0.0000

Data Index: 897150 (C4 (Web Text))

Max Activating Token Index: 189

Text #6

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0774. Min Act: -0.0000

Data Index: 5492 (C4 (Web Text))

Max Activating Token Index: 999

Text #7

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0808. Min Act: -0.0000

Data Index: 556436 (C4 (Web Text))

Max Activating Token Index: 182

Text #8

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0867. Min Act: -0.0000

Data Index: 1201932 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1202898 (C4 (Web Text))

Max Activating Token Index: 824

Text #10

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0871. Min Act: -0.0001

Data Index: 1432600 (Python Code)

Max Activating Token Index: 694

Text #11

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0841. Min Act: 0.0000

Data Index: 1337798 (C4 (Web Text))

Max Activating Token Index: 75

Text #12

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0868. Min Act: -0.0001

Data Index: 1522443 (Python Code)

Max Activating Token Index: 99

Text #13

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0803. Min Act: -0.0001

Data Index: 1513921 (Python Code)

Max Activating Token Index: 106

Text #14

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0823. Min Act: -0.0001

Data Index: 1526789 (Python Code)

Max Activating Token Index: 187

Text #15

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0824. Min Act: -0.0000

Data Index: 806194 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0835. Min Act: -0.0000

Data Index: 897277 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0816. Min Act: -0.0000

Data Index: 575067 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0764. Min Act: -0.0001

Data Index: 1547389 (Python Code)

Max Activating Token Index: 326

Text #19

Max Range: 0.1898. Min Range: -0.1898

Max Act: 0.0703. Min Act: -0.0000

Data Index: 762915 (C4 (Web Text))

Max Activating Token Index: 885