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

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

Neuron 45 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: 0.0472. Min Range: -0.0472

Max Act: 0.0472. Min Act: -0.0001

Data Index: 718154 (C4 (Web Text))

Max Activating Token Index: 158

Text #1

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0443. Min Act: -0.0001

Data Index: 561598 (C4 (Web Text))

Max Activating Token Index: 843

Text #2

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0433. Min Act: -0.0001

Data Index: 94231 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0410. Min Act: -0.0001

Data Index: 996438 (C4 (Web Text))

Max Activating Token Index: 362

Text #4

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0372. Min Act: -0.0002

Data Index: 786123 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0393. Min Act: -0.0001

Data Index: 1320402 (C4 (Web Text))

Max Activating Token Index: 159

Text #6

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0384. Min Act: -0.0002

Data Index: 1026230 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0401. Min Act: -0.0001

Data Index: 73591 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0324. Min Act: -0.0001

Data Index: 102980 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0310. Min Act: -0.0001

Data Index: 177880 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0373. Min Act: -0.0001

Data Index: 114015 (C4 (Web Text))

Max Activating Token Index: 834

Text #11

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0355. Min Act: -0.0001

Data Index: 91829 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0350. Min Act: -0.0001

Data Index: 1060923 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0341. Min Act: -0.0001

Data Index: 859345 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0349. Min Act: -0.0001

Data Index: 695652 (C4 (Web Text))

Max Activating Token Index: 561

Text #15

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0274. Min Act: -0.0001

Data Index: 404554 (C4 (Web Text))

Max Activating Token Index: 314

Text #16

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0335. Min Act: -0.0001

Data Index: 1347446 (C4 (Web Text))

Max Activating Token Index: 978

Text #17

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0314. Min Act: -0.0001

Data Index: 235594 (C4 (Web Text))

Max Activating Token Index: 812

Text #18

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0337. Min Act: -0.0002

Data Index: 1207265 (C4 (Web Text))

Max Activating Token Index: 312

Text #19

Max Range: 0.0472. Min Range: -0.0472

Max Act: 0.0286. Min Act: -0.0001

Data Index: 636992 (C4 (Web Text))

Max Activating Token Index: 410