Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1697 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0627. Min Act: -0.0000

Data Index: 1650777 (Python Code)

Max Activating Token Index: 670

Text #1

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0505. Min Act: -0.0001

Data Index: 27470 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0524. Min Act: -0.0001

Data Index: 1195695 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0493. Min Act: -0.0001

Data Index: 204896 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0454. Min Act: -0.0000

Data Index: 584527 (C4 (Web Text))

Max Activating Token Index: 634

Text #5

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0444. Min Act: -0.0000

Data Index: 1049465 (C4 (Web Text))

Max Activating Token Index: 923

Text #6

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0445. Min Act: -0.0000

Data Index: 905316 (C4 (Web Text))

Max Activating Token Index: 877

Text #7

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0420. Min Act: -0.0000

Data Index: 868755 (C4 (Web Text))

Max Activating Token Index: 329

Text #8

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0440. Min Act: -0.0000

Data Index: 971837 (C4 (Web Text))

Max Activating Token Index: 302

Text #9

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0452. Min Act: -0.0000

Data Index: 333438 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0418. Min Act: -0.0000

Data Index: 575849 (C4 (Web Text))

Max Activating Token Index: 882

Text #11

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0431. Min Act: -0.0000

Data Index: 678153 (C4 (Web Text))

Max Activating Token Index: 28

Text #12

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0464. Min Act: -0.0000

Data Index: 870857 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0458. Min Act: -0.0000

Data Index: 535019 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0416. Min Act: -0.0000

Data Index: 1207026 (C4 (Web Text))

Max Activating Token Index: 108

Text #15

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0438. Min Act: -0.0001

Data Index: 113140 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0398. Min Act: -0.0000

Data Index: 11822 (C4 (Web Text))

Max Activating Token Index: 785

Text #17

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0446. Min Act: -0.0000

Data Index: 1063526 (C4 (Web Text))

Max Activating Token Index: 497

Text #18

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0440. Min Act: -0.0000

Data Index: 148556 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 0.0627. Min Range: -0.0627

Max Act: 0.0437. Min Act: -0.0000

Data Index: 16920 (C4 (Web Text))

Max Activating Token Index: 484