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

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

Neuron 3808 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2356. Min Range: -4.2356

Max Act: 4.2356. Min Act: -0.0000

Data Index: 1053056 (C4 (Web Text))

Max Activating Token Index: 351

Text #1

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.5776. Min Act: -0.0000

Data Index: 655976 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.4651. Min Act: -0.0000

Data Index: 775035 (C4 (Web Text))

Max Activating Token Index: 810

Text #3

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.4226. Min Act: -0.0000

Data Index: 1118391 (C4 (Web Text))

Max Activating Token Index: 247

Text #4

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1775. Min Act: -0.0000

Data Index: 597601 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1650. Min Act: -0.0000

Data Index: 847073 (C4 (Web Text))

Max Activating Token Index: 656

Text #6

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1333. Min Act: -0.0000

Data Index: 1164661 (C4 (Web Text))

Max Activating Token Index: 209

Text #7

Max Range: 4.2356. Min Range: -4.2356

Max Act: 3.1241. Min Act: -0.0000

Data Index: 554689 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.8438. Min Act: -0.0000

Data Index: 1032066 (C4 (Web Text))

Max Activating Token Index: 261

Text #9

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.9681. Min Act: -0.0000

Data Index: 303326 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.9501. Min Act: -0.0000

Data Index: 234696 (C4 (Web Text))

Max Activating Token Index: 122

Text #11

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.9415. Min Act: -0.0000

Data Index: 1278906 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.7254. Min Act: -0.0000

Data Index: 47953 (C4 (Web Text))

Max Activating Token Index: 953

Text #13

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.8378. Min Act: -0.0000

Data Index: 1270737 (C4 (Web Text))

Max Activating Token Index: 66

Text #14

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.7100. Min Act: -0.0000

Data Index: 1006447 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.6818. Min Act: -0.0000

Data Index: 867802 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.6342. Min Act: -0.0000

Data Index: 879037 (C4 (Web Text))

Max Activating Token Index: 346

Text #17

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.6072. Min Act: -0.0000

Data Index: 572183 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.6072. Min Act: -0.0000

Data Index: 696468 (C4 (Web Text))

Max Activating Token Index: 648

Text #19

Max Range: 4.2356. Min Range: -4.2356

Max Act: 2.5841. Min Act: -0.0000

Data Index: 961116 (C4 (Web Text))

Max Activating Token Index: 722