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

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

Neuron 4572 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.8868. Min Act: -0.0000

Data Index: 1000662 (C4 (Web Text))

Max Activating Token Index: 188

Text #1

Max Range: 2.1234. Min Range: -2.1234

Max Act: 2.1234. Min Act: -0.0000

Data Index: 160145 (C4 (Web Text))

Max Activating Token Index: 814

Text #2

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.9839. Min Act: -0.0000

Data Index: 695083 (C4 (Web Text))

Max Activating Token Index: 589

Text #3

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.8523. Min Act: -0.0000

Data Index: 618906 (C4 (Web Text))

Max Activating Token Index: 236

Text #4

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1087837 (C4 (Web Text))

Max Activating Token Index: 858

Text #5

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7447. Min Act: -0.0000

Data Index: 78909 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.8277. Min Act: -0.0000

Data Index: 246921 (C4 (Web Text))

Max Activating Token Index: 390

Text #7

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6275. Min Act: -0.0000

Data Index: 1059133 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6648. Min Act: -0.0000

Data Index: 104397 (C4 (Web Text))

Max Activating Token Index: 283

Text #9

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.9525. Min Act: -0.0000

Data Index: 948745 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4754. Min Act: -0.0000

Data Index: 99041 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5525. Min Act: -0.0000

Data Index: 353796 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.7242. Min Act: -0.0000

Data Index: 1070125 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.6252. Min Act: -0.0000

Data Index: 542378 (C4 (Web Text))

Max Activating Token Index: 740

Text #14

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5295. Min Act: -0.0000

Data Index: 662383 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5160. Min Act: -0.0000

Data Index: 870469 (C4 (Web Text))

Max Activating Token Index: 122

Text #16

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5689. Min Act: -0.0000

Data Index: 182143 (C4 (Web Text))

Max Activating Token Index: 99

Text #17

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5729. Min Act: -0.0000

Data Index: 139923 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.4684. Min Act: -0.0000

Data Index: 141458 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 2.1234. Min Range: -2.1234

Max Act: 1.5412. Min Act: -0.0000

Data Index: 1225604 (C4 (Web Text))

Max Activating Token Index: 202