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

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

Neuron 2915 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: 0.5210. Min Range: -0.5210

Max Act: 0.5210. Min Act: -0.0000

Data Index: 234693 (C4 (Web Text))

Max Activating Token Index: 835

Text #1

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2648. Min Act: -0.0000

Data Index: 1019126 (C4 (Web Text))

Max Activating Token Index: 43

Text #2

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2394. Min Act: -0.0000

Data Index: 438249 (C4 (Web Text))

Max Activating Token Index: 701

Text #3

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2607. Min Act: -0.0001

Data Index: 489549 (C4 (Web Text))

Max Activating Token Index: 50

Text #4

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2343. Min Act: -0.0000

Data Index: 788480 (C4 (Web Text))

Max Activating Token Index: 630

Text #5

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1911. Min Act: -0.0001

Data Index: 1110965 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.2012. Min Act: -0.0000

Data Index: 1135450 (C4 (Web Text))

Max Activating Token Index: 258

Text #7

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1763. Min Act: -0.0001

Data Index: 766479 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1744. Min Act: -0.0001

Data Index: 700433 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1834. Min Act: -0.0000

Data Index: 597335 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1624. Min Act: -0.0000

Data Index: 718272 (C4 (Web Text))

Max Activating Token Index: 273

Text #11

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1615. Min Act: -0.0001

Data Index: 83407 (C4 (Web Text))

Max Activating Token Index: 1003

Text #12

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1600. Min Act: -0.0000

Data Index: 872265 (C4 (Web Text))

Max Activating Token Index: 41

Text #13

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1585. Min Act: -0.0001

Data Index: 983495 (C4 (Web Text))

Max Activating Token Index: 991

Text #14

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1512. Min Act: -0.0000

Data Index: 858751 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1571. Min Act: -0.0001

Data Index: 855265 (C4 (Web Text))

Max Activating Token Index: 290

Text #16

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1572. Min Act: -0.0000

Data Index: 205849 (C4 (Web Text))

Max Activating Token Index: 728

Text #17

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1425. Min Act: -0.0000

Data Index: 238378 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1361. Min Act: -0.0000

Data Index: 309582 (C4 (Web Text))

Max Activating Token Index: 522

Text #19

Max Range: 0.5210. Min Range: -0.5210

Max Act: 0.1359. Min Act: -0.0000

Data Index: 1224980 (C4 (Web Text))

Max Activating Token Index: 808