Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3072 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0561. Min Act: -0.0001

Data Index: 843097 (C4 (Web Text))

Max Activating Token Index: 63

Text #1

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0521. Min Act: -0.0001

Data Index: 881686 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0478. Min Act: -0.0001

Data Index: 1115100 (C4 (Web Text))

Max Activating Token Index: 17

Text #3

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0474. Min Act: -0.0001

Data Index: 978372 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0454. Min Act: -0.0001

Data Index: 296760 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0451. Min Act: -0.0001

Data Index: 163684 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0450. Min Act: -0.0001

Data Index: 1086721 (C4 (Web Text))

Max Activating Token Index: 45

Text #7

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0454. Min Act: -0.0001

Data Index: 1083596 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0456. Min Act: -0.0001

Data Index: 150392 (C4 (Web Text))

Max Activating Token Index: 65

Text #9

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0444. Min Act: -0.0001

Data Index: 393876 (C4 (Web Text))

Max Activating Token Index: 841

Text #10

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0439. Min Act: -0.0001

Data Index: 228182 (C4 (Web Text))

Max Activating Token Index: 152

Text #11

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0437. Min Act: -0.0001

Data Index: 124652 (C4 (Web Text))

Max Activating Token Index: 13

Text #12

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0432. Min Act: -0.0001

Data Index: 467795 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0440. Min Act: -0.0001

Data Index: 603388 (C4 (Web Text))

Max Activating Token Index: 110

Text #14

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0436. Min Act: -0.0001

Data Index: 408250 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0427. Min Act: -0.0001

Data Index: 636487 (C4 (Web Text))

Max Activating Token Index: 752

Text #16

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0431. Min Act: -0.0001

Data Index: 587357 (C4 (Web Text))

Max Activating Token Index: 24

Text #17

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0430. Min Act: -0.0001

Data Index: 826105 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0423. Min Act: -0.0001

Data Index: 340131 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 0.0561. Min Range: -0.0561

Max Act: 0.0433. Min Act: -0.0001

Data Index: 644067 (C4 (Web Text))

Max Activating Token Index: 612