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

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

Neuron 1058 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: 7.9791. Min Range: -7.9791

Max Act: 7.9791. Min Act: -0.0000

Data Index: 622200 (C4 (Web Text))

Max Activating Token Index: 561

Text #1

Max Range: 7.9791. Min Range: -7.9791

Max Act: 7.8972. Min Act: -0.0000

Data Index: 1207419 (C4 (Web Text))

Max Activating Token Index: 845

Text #2

Max Range: 7.9791. Min Range: -7.9791

Max Act: 6.2989. Min Act: -0.0000

Data Index: 126435 (C4 (Web Text))

Max Activating Token Index: 1011

Text #3

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.4728. Min Act: -0.0000

Data Index: 1249960 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.1974. Min Act: -0.0000

Data Index: 1006476 (C4 (Web Text))

Max Activating Token Index: 891

Text #5

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.3653. Min Act: -0.0000

Data Index: 1007733 (C4 (Web Text))

Max Activating Token Index: 933

Text #6

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.1283. Min Act: -0.0000

Data Index: 303724 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.4687. Min Act: -0.0000

Data Index: 659251 (C4 (Web Text))

Max Activating Token Index: 444

Text #8

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.0377. Min Act: -0.0000

Data Index: 172977 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.2203. Min Act: -0.0000

Data Index: 956231 (C4 (Web Text))

Max Activating Token Index: 739

Text #10

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.9302. Min Act: -0.0000

Data Index: 508648 (C4 (Web Text))

Max Activating Token Index: 733

Text #11

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.9449. Min Act: -0.0000

Data Index: 749727 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.5853. Min Act: -0.0000

Data Index: 347309 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 7.9791. Min Range: -7.9791

Max Act: 5.0375. Min Act: -0.0000

Data Index: 158072 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.8999. Min Act: -0.0000

Data Index: 1028432 (C4 (Web Text))

Max Activating Token Index: 341

Text #15

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.8410. Min Act: -0.0000

Data Index: 104254 (C4 (Web Text))

Max Activating Token Index: 98

Text #16

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.7982. Min Act: -0.0000

Data Index: 1297862 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.6109. Min Act: -0.0000

Data Index: 751201 (C4 (Web Text))

Max Activating Token Index: 813

Text #18

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.5138. Min Act: -0.0000

Data Index: 706262 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 7.9791. Min Range: -7.9791

Max Act: 4.5217. Min Act: -0.0000

Data Index: 1094124 (C4 (Web Text))

Max Activating Token Index: 825