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

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

Neuron 1000 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1230844 (C4 (Web Text))

Max Activating Token Index: 249

Text #1

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0402. Min Act: -0.0001

Data Index: 207218 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0357. Min Act: -0.0001

Data Index: 743396 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0359. Min Act: -0.0001

Data Index: 839010 (C4 (Web Text))

Max Activating Token Index: 48

Text #4

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0292. Min Act: -0.0001

Data Index: 261582 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0255. Min Act: -0.0001

Data Index: 358951 (C4 (Web Text))

Max Activating Token Index: 223

Text #6

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0278. Min Act: -0.0001

Data Index: 681234 (C4 (Web Text))

Max Activating Token Index: 216

Text #7

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0279. Min Act: -0.0001

Data Index: 535885 (C4 (Web Text))

Max Activating Token Index: 244

Text #8

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0267. Min Act: -0.0001

Data Index: 623323 (C4 (Web Text))

Max Activating Token Index: 627

Text #9

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0279. Min Act: -0.0001

Data Index: 1151301 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1182815 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0263. Min Act: -0.0001

Data Index: 940364 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0254. Min Act: -0.0001

Data Index: 42086 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0231. Min Act: -0.0001

Data Index: 168164 (C4 (Web Text))

Max Activating Token Index: 228

Text #14

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0241. Min Act: -0.0001

Data Index: 789934 (C4 (Web Text))

Max Activating Token Index: 344

Text #15

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0233. Min Act: -0.0001

Data Index: 871709 (C4 (Web Text))

Max Activating Token Index: 384

Text #16

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0245. Min Act: -0.0001

Data Index: 1255622 (C4 (Web Text))

Max Activating Token Index: 573

Text #17

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0257. Min Act: -0.0001

Data Index: 956743 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0259. Min Act: -0.0001

Data Index: 227168 (C4 (Web Text))

Max Activating Token Index: 581

Text #19

Max Range: 0.0454. Min Range: -0.0454

Max Act: 0.0245. Min Act: -0.0001

Data Index: 458619 (C4 (Web Text))

Max Activating Token Index: 262