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

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

Neuron 1099 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.6346. Min Act: -0.0001

Data Index: 91356 (C4 (Web Text))

Max Activating Token Index: 408

Text #1

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.6417. Min Act: -0.0001

Data Index: 254723 (C4 (Web Text))

Max Activating Token Index: 823

Text #2

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.3165. Min Act: -0.0001

Data Index: 766824 (C4 (Web Text))

Max Activating Token Index: 320

Text #3

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.3690. Min Act: -0.0000

Data Index: 1216505 (C4 (Web Text))

Max Activating Token Index: 414

Text #4

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.4332. Min Act: -0.0000

Data Index: 1174917 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.3952. Min Act: -0.0001

Data Index: 228172 (C4 (Web Text))

Max Activating Token Index: 991

Text #6

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.4247. Min Act: -0.0001

Data Index: 149434 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.3175. Min Act: -0.0001

Data Index: 633049 (C4 (Web Text))

Max Activating Token Index: 467

Text #8

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.3517. Min Act: -0.0001

Data Index: 481788 (C4 (Web Text))

Max Activating Token Index: 897

Text #9

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.3785. Min Act: -0.0001

Data Index: 1040741 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2248. Min Act: -0.0001

Data Index: 863780 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.4036. Min Act: -0.0001

Data Index: 242963 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.1955. Min Act: -0.0001

Data Index: 1344393 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2197. Min Act: -0.0000

Data Index: 735852 (C4 (Web Text))

Max Activating Token Index: 99

Text #14

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2649. Min Act: -0.0000

Data Index: 57610 (C4 (Web Text))

Max Activating Token Index: 781

Text #15

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2053. Min Act: -0.0001

Data Index: 1254697 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2445. Min Act: -0.0001

Data Index: 799632 (C4 (Web Text))

Max Activating Token Index: 326

Text #17

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2279. Min Act: -0.0000

Data Index: 518289 (C4 (Web Text))

Max Activating Token Index: 965

Text #18

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2555. Min Act: -0.0000

Data Index: 353103 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 1.6417. Min Range: -1.6417

Max Act: 1.2633. Min Act: -0.0001

Data Index: 459917 (C4 (Web Text))

Max Activating Token Index: 409