Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1228 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0521. Min Act: -0.0004

Data Index: 947038 (C4 (Web Text))

Max Activating Token Index: 230

Text #1

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0482. Min Act: -0.0004

Data Index: 1344756 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0419. Min Act: -0.0004

Data Index: 1252347 (C4 (Web Text))

Max Activating Token Index: 569

Text #3

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0450. Min Act: -0.0004

Data Index: 1313389 (C4 (Web Text))

Max Activating Token Index: 19

Text #4

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0396. Min Act: -0.0004

Data Index: 564101 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0429. Min Act: -0.0004

Data Index: 344811 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0443. Min Act: -0.0004

Data Index: 532608 (C4 (Web Text))

Max Activating Token Index: 678

Text #7

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0413. Min Act: -0.0004

Data Index: 928157 (C4 (Web Text))

Max Activating Token Index: 804

Text #8

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0355. Min Act: -0.0004

Data Index: 541081 (C4 (Web Text))

Max Activating Token Index: 852

Text #9

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0370. Min Act: -0.0004

Data Index: 1240795 (C4 (Web Text))

Max Activating Token Index: 188

Text #10

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0427. Min Act: -0.0004

Data Index: 1495196 (Python Code)

Max Activating Token Index: 1018

Text #11

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0419. Min Act: -0.0004

Data Index: 1177088 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0392. Min Act: -0.0004

Data Index: 313975 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0354. Min Act: -0.0004

Data Index: 1356912 (C4 (Web Text))

Max Activating Token Index: 653

Text #14

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0419. Min Act: -0.0004

Data Index: 1239700 (C4 (Web Text))

Max Activating Token Index: 840

Text #15

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0415. Min Act: -0.0004

Data Index: 975785 (C4 (Web Text))

Max Activating Token Index: 12

Text #16

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0403. Min Act: -0.0004

Data Index: 624122 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0357. Min Act: -0.0004

Data Index: 1017960 (C4 (Web Text))

Max Activating Token Index: 907

Text #18

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0367. Min Act: -0.0004

Data Index: 757917 (C4 (Web Text))

Max Activating Token Index: 639

Text #19

Max Range: 0.0521. Min Range: -0.0521

Max Act: 0.0383. Min Act: -0.0004

Data Index: 312409 (C4 (Web Text))

Max Activating Token Index: 398