Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 560 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0351. Min Act: -0.0003

Data Index: 970000 (C4 (Web Text))

Max Activating Token Index: 883

Text #1

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0294. Min Act: -0.0002

Data Index: 1163418 (C4 (Web Text))

Max Activating Token Index: 681

Text #2

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0295. Min Act: -0.0002

Data Index: 260304 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0292. Min Act: -0.0002

Data Index: 870721 (C4 (Web Text))

Max Activating Token Index: 175

Text #4

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0278. Min Act: -0.0003

Data Index: 611270 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0286. Min Act: -0.0003

Data Index: 840308 (C4 (Web Text))

Max Activating Token Index: 528

Text #6

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0274. Min Act: -0.0003

Data Index: 560383 (C4 (Web Text))

Max Activating Token Index: 106

Text #7

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0271. Min Act: -0.0003

Data Index: 1221326 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0275. Min Act: -0.0003

Data Index: 1088229 (C4 (Web Text))

Max Activating Token Index: 232

Text #9

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0270. Min Act: -0.0003

Data Index: 959049 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0269. Min Act: -0.0002

Data Index: 485542 (C4 (Web Text))

Max Activating Token Index: 528

Text #11

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0268. Min Act: -0.0001

Data Index: 1354101 (C4 (Web Text))

Max Activating Token Index: 534

Text #12

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0266. Min Act: -0.0004

Data Index: 75295 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0267. Min Act: -0.0002

Data Index: 624564 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0272. Min Act: -0.0001

Data Index: 710415 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0267. Min Act: -0.0003

Data Index: 854732 (C4 (Web Text))

Max Activating Token Index: 878

Text #16

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0261. Min Act: -0.0003

Data Index: 550661 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0271. Min Act: -0.0003

Data Index: 538879 (C4 (Web Text))

Max Activating Token Index: 790

Text #18

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1629109 (Python Code)

Max Activating Token Index: 415

Text #19

Max Range: 0.0351. Min Range: -0.0351

Max Act: 0.0265. Min Act: -0.0002

Data Index: 966721 (C4 (Web Text))

Max Activating Token Index: 648