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

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

Neuron 2145 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.1868. Min Act: -0.0000

Data Index: 275842 (C4 (Web Text))

Max Activating Token Index: 606

Text #1

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.1284. Min Act: 0.0000

Data Index: 1015677 (C4 (Web Text))

Max Activating Token Index: 515

Text #2

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.0686. Min Act: -0.0000

Data Index: 439871 (C4 (Web Text))

Max Activating Token Index: 704

Text #3

Max Range: 1.1868. Min Range: -1.1868

Max Act: 1.0980. Min Act: -0.0000

Data Index: 62330 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9886. Min Act: -0.0000

Data Index: 166749 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9120. Min Act: -0.0000

Data Index: 745291 (C4 (Web Text))

Max Activating Token Index: 311

Text #6

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9937. Min Act: -0.0000

Data Index: 1116647 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9209. Min Act: 0.0000

Data Index: 416248 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8623. Min Act: -0.0000

Data Index: 1040660 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9132. Min Act: -0.0000

Data Index: 444024 (C4 (Web Text))

Max Activating Token Index: 191

Text #10

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8963. Min Act: 0.0000

Data Index: 641599 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9178. Min Act: -0.0000

Data Index: 339321 (C4 (Web Text))

Max Activating Token Index: 593

Text #12

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.9024. Min Act: -0.0000

Data Index: 1058344 (C4 (Web Text))

Max Activating Token Index: 265

Text #13

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8211. Min Act: -0.0000

Data Index: 428925 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8135. Min Act: -0.0000

Data Index: 22431 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.8003. Min Act: -0.0000

Data Index: 574151 (C4 (Web Text))

Max Activating Token Index: 586

Text #16

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.7880. Min Act: 0.0000

Data Index: 947113 (C4 (Web Text))

Max Activating Token Index: 127

Text #17

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.7914. Min Act: 0.0000

Data Index: 617596 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.7810. Min Act: 0.0000

Data Index: 1214695 (C4 (Web Text))

Max Activating Token Index: 679

Text #19

Max Range: 1.1868. Min Range: -1.1868

Max Act: 0.7753. Min Act: 0.0000

Data Index: 161862 (C4 (Web Text))

Max Activating Token Index: 710