Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1548 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.3271. Min Act: -0.0001

Data Index: 17505 (C4 (Web Text))

Max Activating Token Index: 538

Text #1

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2682. Min Act: -0.0001

Data Index: 1351828 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2647. Min Act: -0.0001

Data Index: 799468 (C4 (Web Text))

Max Activating Token Index: 524

Text #3

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2826. Min Act: -0.0001

Data Index: 477002 (C4 (Web Text))

Max Activating Token Index: 936

Text #4

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2675. Min Act: -0.0001

Data Index: 1338149 (C4 (Web Text))

Max Activating Token Index: 780

Text #5

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2464. Min Act: -0.0001

Data Index: 642578 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2429. Min Act: -0.0001

Data Index: 594411 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2429. Min Act: -0.0001

Data Index: 778792 (C4 (Web Text))

Max Activating Token Index: 584

Text #8

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2426. Min Act: -0.0001

Data Index: 410082 (C4 (Web Text))

Max Activating Token Index: 459

Text #9

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2168. Min Act: -0.0001

Data Index: 955118 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2229. Min Act: -0.0001

Data Index: 328737 (C4 (Web Text))

Max Activating Token Index: 4

Text #11

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2209. Min Act: -0.0001

Data Index: 283635 (C4 (Web Text))

Max Activating Token Index: 275

Text #12

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2218. Min Act: -0.0001

Data Index: 1074057 (C4 (Web Text))

Max Activating Token Index: 371

Text #13

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2212. Min Act: -0.0001

Data Index: 547613 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2344. Min Act: -0.0001

Data Index: 478695 (C4 (Web Text))

Max Activating Token Index: 867

Text #15

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2238. Min Act: -0.0001

Data Index: 526917 (C4 (Web Text))

Max Activating Token Index: 911

Text #16

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2214. Min Act: -0.0001

Data Index: 811772 (C4 (Web Text))

Max Activating Token Index: 74

Text #17

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2137. Min Act: -0.0001

Data Index: 877507 (C4 (Web Text))

Max Activating Token Index: 524

Text #18

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1315805 (C4 (Web Text))

Max Activating Token Index: 412

Text #19

Max Range: 0.3271. Min Range: -0.3271

Max Act: 0.1876. Min Act: -0.0001

Data Index: 106081 (C4 (Web Text))

Max Activating Token Index: 772