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

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

Neuron 4355 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.7621. Min Act: -0.0000

Data Index: 1379723 (Python Code)

Max Activating Token Index: 566

Text #1

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.9251. Min Act: -0.0000

Data Index: 1408153 (Python Code)

Max Activating Token Index: 485

Text #2

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.7148. Min Act: -0.0000

Data Index: 1453845 (Python Code)

Max Activating Token Index: 611

Text #3

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.6228. Min Act: -0.0000

Data Index: 1393627 (Python Code)

Max Activating Token Index: 179

Text #4

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.1864. Min Act: -0.0000

Data Index: 1371649 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.1868. Min Act: -0.0000

Data Index: 1530191 (Python Code)

Max Activating Token Index: 821

Text #6

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.5302. Min Act: -0.0000

Data Index: 1643697 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.1261. Min Act: -0.0000

Data Index: 1621973 (Python Code)

Max Activating Token Index: 609

Text #8

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.6627. Min Act: -0.0000

Data Index: 1403871 (Python Code)

Max Activating Token Index: 252

Text #9

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.1043. Min Act: -0.0000

Data Index: 1520078 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.0777. Min Act: -0.0000

Data Index: 1422446 (Python Code)

Max Activating Token Index: 576

Text #11

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.0820. Min Act: -0.0000

Data Index: 1527403 (Python Code)

Max Activating Token Index: 711

Text #12

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.2473. Min Act: -0.0000

Data Index: 1468607 (Python Code)

Max Activating Token Index: 406

Text #13

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.2358. Min Act: -0.0000

Data Index: 1621398 (Python Code)

Max Activating Token Index: 517

Text #14

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.0295. Min Act: -0.0000

Data Index: 1576925 (Python Code)

Max Activating Token Index: 519

Text #15

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.2066. Min Act: -0.0000

Data Index: 1464567 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.1969. Min Act: -0.0000

Data Index: 1415937 (Python Code)

Max Activating Token Index: 611

Text #17

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.0199. Min Act: -0.0000

Data Index: 1490008 (Python Code)

Max Activating Token Index: 597

Text #18

Max Range: 5.9251. Min Range: -5.9251

Max Act: 4.8479. Min Act: -0.0000

Data Index: 1600781 (Python Code)

Max Activating Token Index: 440

Text #19

Max Range: 5.9251. Min Range: -5.9251

Max Act: 5.1628. Min Act: -0.0000

Data Index: 1397616 (Python Code)

Max Activating Token Index: 521