Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 376 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0293. Min Act: -0.0006

Data Index: 259925 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0294. Min Act: -0.0006

Data Index: 113861 (C4 (Web Text))

Max Activating Token Index: 375

Text #2

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0287. Min Act: -0.0006

Data Index: 660427 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0277. Min Act: -0.0006

Data Index: 1307518 (C4 (Web Text))

Max Activating Token Index: 869

Text #4

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0277. Min Act: -0.0006

Data Index: 849550 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0277. Min Act: -0.0006

Data Index: 153971 (C4 (Web Text))

Max Activating Token Index: 77

Text #6

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0270. Min Act: -0.0006

Data Index: 525949 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0264. Min Act: -0.0006

Data Index: 950081 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0271. Min Act: -0.0006

Data Index: 479266 (C4 (Web Text))

Max Activating Token Index: 740

Text #9

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0265. Min Act: -0.0006

Data Index: 777108 (C4 (Web Text))

Max Activating Token Index: 552

Text #10

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0262. Min Act: -0.0006

Data Index: 34635 (C4 (Web Text))

Max Activating Token Index: 211

Text #11

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0267. Min Act: -0.0006

Data Index: 563836 (C4 (Web Text))

Max Activating Token Index: 843

Text #12

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0259. Min Act: -0.0006

Data Index: 448274 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0265. Min Act: -0.0006

Data Index: 646056 (C4 (Web Text))

Max Activating Token Index: 100

Text #14

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0264. Min Act: -0.0006

Data Index: 1125165 (C4 (Web Text))

Max Activating Token Index: 427

Text #15

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0254. Min Act: -0.0006

Data Index: 330200 (C4 (Web Text))

Max Activating Token Index: 735

Text #16

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0257. Min Act: -0.0006

Data Index: 939575 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0258. Min Act: -0.0006

Data Index: 891436 (C4 (Web Text))

Max Activating Token Index: 306

Text #18

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0257. Min Act: -0.0006

Data Index: 917796 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.0294. Min Range: -0.0294

Max Act: 0.0263. Min Act: -0.0006

Data Index: 397421 (C4 (Web Text))

Max Activating Token Index: 194