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

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

Neuron 2353 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.8210. Min Act: -0.0000

Data Index: 436855 (C4 (Web Text))

Max Activating Token Index: 863

Text #1

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.8172. Min Act: -0.0000

Data Index: 272094 (C4 (Web Text))

Max Activating Token Index: 443

Text #2

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.8199. Min Act: -0.0000

Data Index: 376256 (C4 (Web Text))

Max Activating Token Index: 410

Text #3

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.7797. Min Act: -0.0000

Data Index: 830750 (C4 (Web Text))

Max Activating Token Index: 831

Text #4

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.7863. Min Act: -0.0000

Data Index: 1486856 (Python Code)

Max Activating Token Index: 757

Text #5

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.7914. Min Act: -0.0000

Data Index: 1493841 (Python Code)

Max Activating Token Index: 320

Text #6

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1351605 (C4 (Web Text))

Max Activating Token Index: 260

Text #7

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1565553 (Python Code)

Max Activating Token Index: 212

Text #8

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6441. Min Act: -0.0000

Data Index: 1501415 (Python Code)

Max Activating Token Index: 370

Text #9

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6290. Min Act: -0.0000

Data Index: 44957 (C4 (Web Text))

Max Activating Token Index: 452

Text #10

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1415157 (Python Code)

Max Activating Token Index: 373

Text #11

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6876. Min Act: -0.0000

Data Index: 1381887 (Python Code)

Max Activating Token Index: 522

Text #12

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5852. Min Act: -0.0000

Data Index: 203816 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6251. Min Act: -0.0000

Data Index: 1376374 (Python Code)

Max Activating Token Index: 434

Text #14

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5804. Min Act: -0.0000

Data Index: 742612 (C4 (Web Text))

Max Activating Token Index: 964

Text #15

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1361181 (Python Code)

Max Activating Token Index: 461

Text #16

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6239. Min Act: -0.0000

Data Index: 1416368 (Python Code)

Max Activating Token Index: 646

Text #17

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.6044. Min Act: -0.0000

Data Index: 1484445 (Python Code)

Max Activating Token Index: 876

Text #18

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1522836 (Python Code)

Max Activating Token Index: 324

Text #19

Max Range: 0.8210. Min Range: -0.8210

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1452111 (Python Code)

Max Activating Token Index: 433