Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1537 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.2201. Min Range: -3.2201

Max Act: 3.2201. Min Act: -0.0000

Data Index: 811921 (C4 (Web Text))

Max Activating Token Index: 800

Text #1

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.4081. Min Act: -0.0000

Data Index: 477635 (C4 (Web Text))

Max Activating Token Index: 138

Text #2

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.3750. Min Act: -0.0000

Data Index: 856002 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.0958. Min Act: -0.0000

Data Index: 1260819 (C4 (Web Text))

Max Activating Token Index: 210

Text #4

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.2965. Min Act: -0.0000

Data Index: 739290 (C4 (Web Text))

Max Activating Token Index: 338

Text #5

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.2761. Min Act: -0.0000

Data Index: 1051493 (C4 (Web Text))

Max Activating Token Index: 811

Text #6

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.1441. Min Act: -0.0000

Data Index: 988143 (C4 (Web Text))

Max Activating Token Index: 315

Text #7

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.0119. Min Act: -0.0000

Data Index: 361477 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.0909. Min Act: -0.0000

Data Index: 616113 (C4 (Web Text))

Max Activating Token Index: 1001

Text #9

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.9406. Min Act: -0.0000

Data Index: 505472 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.0203. Min Act: -0.0000

Data Index: 442337 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.9826. Min Act: -0.0000

Data Index: 137615 (C4 (Web Text))

Max Activating Token Index: 895

Text #12

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.9683. Min Act: -0.0000

Data Index: 688019 (C4 (Web Text))

Max Activating Token Index: 324

Text #13

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.9701. Min Act: -0.0000

Data Index: 198808 (C4 (Web Text))

Max Activating Token Index: 527

Text #14

Max Range: 3.2201. Min Range: -3.2201

Max Act: 2.0670. Min Act: -0.0000

Data Index: 30784 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.8385. Min Act: -0.0000

Data Index: 901409 (C4 (Web Text))

Max Activating Token Index: 312

Text #16

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.8367. Min Act: -0.0000

Data Index: 96010 (C4 (Web Text))

Max Activating Token Index: 608

Text #17

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.8856. Min Act: -0.0000

Data Index: 449542 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.8839. Min Act: -0.0000

Data Index: 404025 (C4 (Web Text))

Max Activating Token Index: 912

Text #19

Max Range: 3.2201. Min Range: -3.2201

Max Act: 1.8995. Min Act: -0.0000

Data Index: 79567 (C4 (Web Text))

Max Activating Token Index: 498