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

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

Neuron 122 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.9838. Min Act: -0.0001

Data Index: 360708 (C4 (Web Text))

Max Activating Token Index: 588

Text #1

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.9728. Min Act: -0.0001

Data Index: 416814 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.8456. Min Act: -0.0001

Data Index: 640701 (C4 (Web Text))

Max Activating Token Index: 971

Text #3

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.6430. Min Act: -0.0001

Data Index: 1284141 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.5882. Min Act: -0.0001

Data Index: 837801 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.4827. Min Act: -0.0001

Data Index: 1345379 (C4 (Web Text))

Max Activating Token Index: 842

Text #6

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.3146. Min Act: -0.0001

Data Index: 1235429 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.7714. Min Act: -0.0001

Data Index: 136266 (C4 (Web Text))

Max Activating Token Index: 664

Text #8

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.5947. Min Act: -0.0001

Data Index: 894935 (C4 (Web Text))

Max Activating Token Index: 756

Text #9

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.1869. Min Act: -0.0001

Data Index: 1045033 (C4 (Web Text))

Max Activating Token Index: 805

Text #10

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.3294. Min Act: -0.0001

Data Index: 605061 (C4 (Web Text))

Max Activating Token Index: 394

Text #11

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.4044. Min Act: -0.0001

Data Index: 918026 (C4 (Web Text))

Max Activating Token Index: 452

Text #12

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.4417. Min Act: -0.0001

Data Index: 300714 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.5417. Min Act: -0.0001

Data Index: 1003032 (C4 (Web Text))

Max Activating Token Index: 661

Text #14

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.5788. Min Act: -0.0001

Data Index: 441320 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.2716. Min Act: -0.0001

Data Index: 795115 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.2289. Min Act: -0.0001

Data Index: 281567 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 3.9838. Min Range: -3.9838

Max Act: 2.8292. Min Act: -0.0001

Data Index: 77161 (C4 (Web Text))

Max Activating Token Index: 401

Text #18

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.3100. Min Act: -0.0001

Data Index: 596052 (C4 (Web Text))

Max Activating Token Index: 154

Text #19

Max Range: 3.9838. Min Range: -3.9838

Max Act: 3.1803. Min Act: -0.0001

Data Index: 639497 (C4 (Web Text))

Max Activating Token Index: 405