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

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

Neuron 4800 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: 0.2044. Min Range: -0.2044

Max Act: 0.2044. Min Act: -0.0002

Data Index: 281835 (C4 (Web Text))

Max Activating Token Index: 896

Text #1

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1797. Min Act: -0.0002

Data Index: 825024 (C4 (Web Text))

Max Activating Token Index: 818

Text #2

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1659. Min Act: -0.0002

Data Index: 1109076 (C4 (Web Text))

Max Activating Token Index: 644

Text #3

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1687. Min Act: -0.0002

Data Index: 1000057 (C4 (Web Text))

Max Activating Token Index: 112

Text #4

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1644. Min Act: -0.0002

Data Index: 871310 (C4 (Web Text))

Max Activating Token Index: 427

Text #5

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1560. Min Act: -0.0002

Data Index: 359995 (C4 (Web Text))

Max Activating Token Index: 151

Text #6

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1518. Min Act: -0.0002

Data Index: 267455 (C4 (Web Text))

Max Activating Token Index: 847

Text #7

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1503. Min Act: -0.0002

Data Index: 1222237 (C4 (Web Text))

Max Activating Token Index: 1003

Text #8

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1498. Min Act: -0.0002

Data Index: 761064 (C4 (Web Text))

Max Activating Token Index: 881

Text #9

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1488. Min Act: -0.0002

Data Index: 58009 (C4 (Web Text))

Max Activating Token Index: 68

Text #10

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1458. Min Act: -0.0002

Data Index: 303720 (C4 (Web Text))

Max Activating Token Index: 128

Text #11

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1531. Min Act: -0.0002

Data Index: 322051 (C4 (Web Text))

Max Activating Token Index: 378

Text #12

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1381. Min Act: -0.0002

Data Index: 59045 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1378. Min Act: -0.0002

Data Index: 687518 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1421. Min Act: -0.0002

Data Index: 1162696 (C4 (Web Text))

Max Activating Token Index: 473

Text #15

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1399. Min Act: -0.0002

Data Index: 1294931 (C4 (Web Text))

Max Activating Token Index: 28

Text #16

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1393. Min Act: -0.0002

Data Index: 297982 (C4 (Web Text))

Max Activating Token Index: 611

Text #17

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1358. Min Act: -0.0002

Data Index: 880700 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1419. Min Act: -0.0002

Data Index: 461877 (C4 (Web Text))

Max Activating Token Index: 931

Text #19

Max Range: 0.2044. Min Range: -0.2044

Max Act: 0.1385. Min Act: -0.0002

Data Index: 978560 (C4 (Web Text))

Max Activating Token Index: 84