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

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

Neuron 241 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.8468. Min Act: -0.0000

Data Index: 466235 (C4 (Web Text))

Max Activating Token Index: 353

Text #1

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.5667. Min Act: -0.0000

Data Index: 780561 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6676. Min Act: -0.0000

Data Index: 867587 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6359. Min Act: -0.0000

Data Index: 229071 (C4 (Web Text))

Max Activating Token Index: 710

Text #4

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.6137. Min Act: -0.0000

Data Index: 1157246 (C4 (Web Text))

Max Activating Token Index: 678

Text #5

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.4309. Min Act: -0.0000

Data Index: 586835 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.4214. Min Act: -0.0000

Data Index: 1028080 (C4 (Web Text))

Max Activating Token Index: 267

Text #7

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.2962. Min Act: -0.0000

Data Index: 907527 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.3254. Min Act: -0.0000

Data Index: 17762 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.3279. Min Act: -0.0000

Data Index: 671959 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.3225. Min Act: -0.0000

Data Index: 557513 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.4343. Min Act: -0.0000

Data Index: 1006650 (C4 (Web Text))

Max Activating Token Index: 92

Text #12

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.2189. Min Act: -0.0000

Data Index: 730284 (C4 (Web Text))

Max Activating Token Index: 725

Text #13

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.2144. Min Act: -0.0000

Data Index: 885463 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.3196. Min Act: -0.0000

Data Index: 920532 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.2234. Min Act: -0.0000

Data Index: 337169 (C4 (Web Text))

Max Activating Token Index: 968

Text #16

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.1351. Min Act: -0.0000

Data Index: 627755 (C4 (Web Text))

Max Activating Token Index: 524

Text #17

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.0453. Min Act: -0.0000

Data Index: 1003677 (C4 (Web Text))

Max Activating Token Index: 332

Text #18

Max Range: 2.8468. Min Range: -2.8468

Max Act: 2.0161. Min Act: -0.0000

Data Index: 499960 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 2.8468. Min Range: -2.8468

Max Act: 1.8963. Min Act: -0.0000

Data Index: 537937 (C4 (Web Text))

Max Activating Token Index: 227