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

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

Neuron 648 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0456. Min Act: -0.0003

Data Index: 94386 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0438. Min Act: -0.0003

Data Index: 1120391 (C4 (Web Text))

Max Activating Token Index: 49

Text #2

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0415. Min Act: -0.0003

Data Index: 1326599 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0412. Min Act: -0.0003

Data Index: 389383 (C4 (Web Text))

Max Activating Token Index: 858

Text #4

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0420. Min Act: -0.0003

Data Index: 373343 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0401. Min Act: -0.0003

Data Index: 788073 (C4 (Web Text))

Max Activating Token Index: 135

Text #6

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0424. Min Act: -0.0003

Data Index: 1001217 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0387. Min Act: -0.0004

Data Index: 965474 (C4 (Web Text))

Max Activating Token Index: 732

Text #8

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0396. Min Act: -0.0003

Data Index: 202829 (C4 (Web Text))

Max Activating Token Index: 257

Text #9

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0394. Min Act: -0.0003

Data Index: 1101431 (C4 (Web Text))

Max Activating Token Index: 12

Text #10

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0378. Min Act: -0.0004

Data Index: 808939 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0390. Min Act: -0.0003

Data Index: 749963 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0383. Min Act: -0.0003

Data Index: 1072956 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0386. Min Act: -0.0003

Data Index: 514154 (C4 (Web Text))

Max Activating Token Index: 955

Text #14

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0385. Min Act: -0.0003

Data Index: 1347575 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0367. Min Act: -0.0003

Data Index: 1172798 (C4 (Web Text))

Max Activating Token Index: 845

Text #16

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0379. Min Act: -0.0003

Data Index: 1129909 (C4 (Web Text))

Max Activating Token Index: 67

Text #17

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0370. Min Act: -0.0003

Data Index: 1246745 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0367. Min Act: -0.0003

Data Index: 367838 (C4 (Web Text))

Max Activating Token Index: 605

Text #19

Max Range: 0.0456. Min Range: -0.0456

Max Act: 0.0376. Min Act: -0.0003

Data Index: 1129714 (C4 (Web Text))

Max Activating Token Index: 512