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

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

Neuron 3200 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3687. Min Act: -0.0000

Data Index: 1024551 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3970. Min Act: -0.0000

Data Index: 370126 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3442. Min Act: -0.0000

Data Index: 1169973 (C4 (Web Text))

Max Activating Token Index: 298

Text #3

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3509. Min Act: -0.0000

Data Index: 1288305 (C4 (Web Text))

Max Activating Token Index: 961

Text #4

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3611. Min Act: -0.0000

Data Index: 211882 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3134. Min Act: -0.0000

Data Index: 287774 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3584. Min Act: -0.0000

Data Index: 194274 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3445. Min Act: -0.0000

Data Index: 1004428 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3411. Min Act: -0.0000

Data Index: 857988 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3310. Min Act: -0.0000

Data Index: 473736 (C4 (Web Text))

Max Activating Token Index: 86

Text #10

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3422. Min Act: -0.0000

Data Index: 1218190 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3512. Min Act: -0.0000

Data Index: 309594 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3402. Min Act: -0.0000

Data Index: 1207857 (C4 (Web Text))

Max Activating Token Index: 74

Text #13

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3373. Min Act: -0.0000

Data Index: 722586 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3346. Min Act: -0.0000

Data Index: 363740 (C4 (Web Text))

Max Activating Token Index: 656

Text #15

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3234. Min Act: -0.0000

Data Index: 592106 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3354. Min Act: -0.0000

Data Index: 457972 (C4 (Web Text))

Max Activating Token Index: 68

Text #17

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3452. Min Act: -0.0000

Data Index: 126060 (C4 (Web Text))

Max Activating Token Index: 391

Text #18

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3209. Min Act: -0.0000

Data Index: 674374 (C4 (Web Text))

Max Activating Token Index: 657

Text #19

Max Range: 0.3970. Min Range: -0.3970

Max Act: 0.3321. Min Act: -0.0000

Data Index: 695998 (C4 (Web Text))

Max Activating Token Index: 984