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

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

Neuron 3384 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3996. Min Act: -0.0001

Data Index: 512865 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3053. Min Act: -0.0001

Data Index: 743493 (C4 (Web Text))

Max Activating Token Index: 680

Text #2

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3306. Min Act: -0.0001

Data Index: 165856 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.3437. Min Act: -0.0001

Data Index: 1288645 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2795. Min Act: -0.0001

Data Index: 1034236 (C4 (Web Text))

Max Activating Token Index: 592

Text #5

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2729. Min Act: -0.0001

Data Index: 886595 (C4 (Web Text))

Max Activating Token Index: 490

Text #6

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2580. Min Act: -0.0001

Data Index: 958118 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2528. Min Act: -0.0001

Data Index: 331668 (C4 (Web Text))

Max Activating Token Index: 663

Text #8

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2558. Min Act: -0.0000

Data Index: 714715 (C4 (Web Text))

Max Activating Token Index: 42

Text #9

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2464. Min Act: -0.0001

Data Index: 384976 (C4 (Web Text))

Max Activating Token Index: 541

Text #10

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2462. Min Act: -0.0001

Data Index: 379041 (C4 (Web Text))

Max Activating Token Index: 704

Text #11

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2517. Min Act: -0.0000

Data Index: 329206 (C4 (Web Text))

Max Activating Token Index: 776

Text #12

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2565. Min Act: -0.0001

Data Index: 784620 (C4 (Web Text))

Max Activating Token Index: 681

Text #13

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2429. Min Act: -0.0000

Data Index: 988442 (C4 (Web Text))

Max Activating Token Index: 486

Text #14

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2351. Min Act: -0.0000

Data Index: 887787 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2250. Min Act: -0.0000

Data Index: 136557 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2281. Min Act: -0.0001

Data Index: 773057 (C4 (Web Text))

Max Activating Token Index: 474

Text #17

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2257. Min Act: -0.0001

Data Index: 1006796 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2233. Min Act: -0.0001

Data Index: 9258 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.3996. Min Range: -0.3996

Max Act: 0.2094. Min Act: -0.0001

Data Index: 1585227 (Python Code)

Max Activating Token Index: 784