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

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

Neuron 366 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0311. Min Act: -0.0002

Data Index: 1471164 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0297. Min Act: -0.0002

Data Index: 455607 (C4 (Web Text))

Max Activating Token Index: 941

Text #2

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0293. Min Act: -0.0002

Data Index: 304005 (C4 (Web Text))

Max Activating Token Index: 147

Text #3

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1409059 (Python Code)

Max Activating Token Index: 202

Text #4

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0286. Min Act: -0.0003

Data Index: 564064 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1113461 (C4 (Web Text))

Max Activating Token Index: 209

Text #6

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1589894 (Python Code)

Max Activating Token Index: 159

Text #7

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1234418 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0002

Data Index: 1370477 (Python Code)

Max Activating Token Index: 21

Text #9

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1396044 (Python Code)

Max Activating Token Index: 18

Text #10

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1417294 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0270. Min Act: -0.0002

Data Index: 1512055 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1484355 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0002

Data Index: 618639 (C4 (Web Text))

Max Activating Token Index: 96

Text #14

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0002

Data Index: 449065 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0268. Min Act: -0.0003

Data Index: 207156 (C4 (Web Text))

Max Activating Token Index: 112

Text #16

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0266. Min Act: -0.0002

Data Index: 659723 (C4 (Web Text))

Max Activating Token Index: 22

Text #17

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0265. Min Act: -0.0003

Data Index: 335375 (C4 (Web Text))

Max Activating Token Index: 517

Text #18

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1504179 (Python Code)

Max Activating Token Index: 21

Text #19

Max Range: 0.0311. Min Range: -0.0311

Max Act: 0.0261. Min Act: -0.0002

Data Index: 1424970 (Python Code)

Max Activating Token Index: 330