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

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

Neuron 506 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1048354 (C4 (Web Text))

Max Activating Token Index: 70

Text #1

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.6207. Min Act: -0.0000

Data Index: 649678 (C4 (Web Text))

Max Activating Token Index: 616

Text #2

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5818. Min Act: -0.0000

Data Index: 579295 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5511. Min Act: -0.0000

Data Index: 129874 (C4 (Web Text))

Max Activating Token Index: 262

Text #4

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5577. Min Act: -0.0000

Data Index: 315730 (C4 (Web Text))

Max Activating Token Index: 469

Text #5

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5686. Min Act: -0.0000

Data Index: 988552 (C4 (Web Text))

Max Activating Token Index: 421

Text #6

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1327326 (C4 (Web Text))

Max Activating Token Index: 806

Text #7

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5265. Min Act: -0.0000

Data Index: 46255 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5020. Min Act: -0.0000

Data Index: 309032 (C4 (Web Text))

Max Activating Token Index: 843

Text #9

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.5391. Min Act: -0.0000

Data Index: 1346781 (C4 (Web Text))

Max Activating Token Index: 262

Text #10

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4990. Min Act: -0.0000

Data Index: 834795 (C4 (Web Text))

Max Activating Token Index: 747

Text #11

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4783. Min Act: 0.0000

Data Index: 556007 (C4 (Web Text))

Max Activating Token Index: 285

Text #12

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4751. Min Act: -0.0000

Data Index: 75417 (C4 (Web Text))

Max Activating Token Index: 55

Text #13

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4699. Min Act: -0.0000

Data Index: 1043708 (C4 (Web Text))

Max Activating Token Index: 827

Text #14

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4724. Min Act: -0.0000

Data Index: 1011498 (C4 (Web Text))

Max Activating Token Index: 288

Text #15

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4661. Min Act: -0.0000

Data Index: 500265 (C4 (Web Text))

Max Activating Token Index: 959

Text #16

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4621. Min Act: -0.0000

Data Index: 70909 (C4 (Web Text))

Max Activating Token Index: 45

Text #17

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4617. Min Act: -0.0000

Data Index: 1241544 (C4 (Web Text))

Max Activating Token Index: 254

Text #18

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4730. Min Act: 0.0000

Data Index: 768824 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.6247. Min Range: -0.6247

Max Act: 0.4410. Min Act: -0.0000

Data Index: 549715 (C4 (Web Text))

Max Activating Token Index: 1003