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

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

Neuron 4516 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: 3.1726. Min Range: -3.1726

Max Act: 3.1726. Min Act: -0.0000

Data Index: 135318 (C4 (Web Text))

Max Activating Token Index: 275

Text #1

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.9410. Min Act: -0.0000

Data Index: 795115 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 3.1726. Min Range: -3.1726

Max Act: 3.0905. Min Act: -0.0000

Data Index: 1195402 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.7606. Min Act: -0.0000

Data Index: 1038875 (C4 (Web Text))

Max Activating Token Index: 83

Text #4

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.5951. Min Act: -0.0000

Data Index: 503060 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.6831. Min Act: -0.0000

Data Index: 803427 (C4 (Web Text))

Max Activating Token Index: 106

Text #6

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.5062. Min Act: -0.0000

Data Index: 1345379 (C4 (Web Text))

Max Activating Token Index: 842

Text #7

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.6244. Min Act: -0.0000

Data Index: 1309370 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.6198. Min Act: -0.0000

Data Index: 1151554 (C4 (Web Text))

Max Activating Token Index: 693

Text #9

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.5913. Min Act: -0.0000

Data Index: 315363 (C4 (Web Text))

Max Activating Token Index: 1006

Text #10

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.4197. Min Act: -0.0000

Data Index: 415583 (C4 (Web Text))

Max Activating Token Index: 816

Text #11

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.3985. Min Act: -0.0000

Data Index: 1317239 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.3888. Min Act: -0.0000

Data Index: 271756 (C4 (Web Text))

Max Activating Token Index: 866

Text #13

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.5109. Min Act: -0.0000

Data Index: 772167 (C4 (Web Text))

Max Activating Token Index: 941

Text #14

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.4965. Min Act: -0.0000

Data Index: 247702 (C4 (Web Text))

Max Activating Token Index: 450

Text #15

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.5002. Min Act: -0.0000

Data Index: 529733 (C4 (Web Text))

Max Activating Token Index: 1016

Text #16

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.3609. Min Act: -0.0000

Data Index: 513232 (C4 (Web Text))

Max Activating Token Index: 621

Text #17

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.4765. Min Act: -0.0000

Data Index: 1046903 (C4 (Web Text))

Max Activating Token Index: 714

Text #18

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.4604. Min Act: -0.0000

Data Index: 1005329 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 3.1726. Min Range: -3.1726

Max Act: 2.3203. Min Act: -0.0000

Data Index: 885139 (C4 (Web Text))

Max Activating Token Index: 325