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

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

Neuron 1677 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0453. Min Act: -0.0005

Data Index: 1076712 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0427. Min Act: -0.0004

Data Index: 1421588 (Python Code)

Max Activating Token Index: 912

Text #2

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0415. Min Act: -0.0004

Data Index: 1197622 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0386. Min Act: -0.0004

Data Index: 367913 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0395. Min Act: -0.0004

Data Index: 426015 (C4 (Web Text))

Max Activating Token Index: 1005

Text #5

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0391. Min Act: -0.0004

Data Index: 1038249 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0395. Min Act: -0.0004

Data Index: 556200 (C4 (Web Text))

Max Activating Token Index: 1017

Text #7

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0388. Min Act: -0.0004

Data Index: 880207 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0392. Min Act: -0.0004

Data Index: 1575383 (Python Code)

Max Activating Token Index: 896

Text #9

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0397. Min Act: -0.0004

Data Index: 342869 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0394. Min Act: -0.0004

Data Index: 789289 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0368. Min Act: -0.0004

Data Index: 1434715 (Python Code)

Max Activating Token Index: 1004

Text #12

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0377. Min Act: -0.0004

Data Index: 74807 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0383. Min Act: -0.0004

Data Index: 537952 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0384. Min Act: -0.0004

Data Index: 126426 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0368. Min Act: -0.0004

Data Index: 1204276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0403. Min Act: -0.0004

Data Index: 266101 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0372. Min Act: -0.0005

Data Index: 1149897 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0370. Min Act: -0.0004

Data Index: 830304 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0453. Min Range: -0.0453

Max Act: 0.0331. Min Act: -0.0004

Data Index: 676141 (C4 (Web Text))

Max Activating Token Index: 1023