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

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

Neuron 3792 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 829367 (C4 (Web Text))

Max Activating Token Index: 838

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0496. Min Act: -0.0002

Data Index: 114543 (C4 (Web Text))

Max Activating Token Index: 625

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0494. Min Act: -0.0002

Data Index: 200008 (C4 (Web Text))

Max Activating Token Index: 736

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0476. Min Act: -0.0002

Data Index: 1060319 (C4 (Web Text))

Max Activating Token Index: 8

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0483. Min Act: -0.0002

Data Index: 59612 (C4 (Web Text))

Max Activating Token Index: 112

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0455. Min Act: -0.0002

Data Index: 95566 (C4 (Web Text))

Max Activating Token Index: 680

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0441. Min Act: -0.0002

Data Index: 612897 (C4 (Web Text))

Max Activating Token Index: 919

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0431. Min Act: -0.0002

Data Index: 791094 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0414. Min Act: -0.0002

Data Index: 406337 (C4 (Web Text))

Max Activating Token Index: 757

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0438. Min Act: -0.0002

Data Index: 281533 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0414. Min Act: -0.0002

Data Index: 825590 (C4 (Web Text))

Max Activating Token Index: 414

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0416. Min Act: -0.0002

Data Index: 87993 (C4 (Web Text))

Max Activating Token Index: 457

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0409. Min Act: -0.0002

Data Index: 332814 (C4 (Web Text))

Max Activating Token Index: 38

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0422. Min Act: -0.0002

Data Index: 773442 (C4 (Web Text))

Max Activating Token Index: 199

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0412. Min Act: -0.0002

Data Index: 899217 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0400. Min Act: -0.0002

Data Index: 958737 (C4 (Web Text))

Max Activating Token Index: 834

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0401. Min Act: -0.0002

Data Index: 321777 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0410. Min Act: -0.0002

Data Index: 839809 (C4 (Web Text))

Max Activating Token Index: 29

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0391. Min Act: -0.0002

Data Index: 68717 (C4 (Web Text))

Max Activating Token Index: 631

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0377. Min Act: -0.0002

Data Index: 337159 (C4 (Web Text))

Max Activating Token Index: 235