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

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

Neuron 4 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: 6.1037. Min Range: -6.1037

Max Act: 6.1037. Min Act: -0.0000

Data Index: 1487878 (Python Code)

Max Activating Token Index: 911

Text #1

Max Range: 6.1037. Min Range: -6.1037

Max Act: 5.6200. Min Act: -0.0000

Data Index: 1652630 (Python Code)

Max Activating Token Index: 604

Text #2

Max Range: 6.1037. Min Range: -6.1037

Max Act: 5.4418. Min Act: -0.0000

Data Index: 1646530 (Python Code)

Max Activating Token Index: 812

Text #3

Max Range: 6.1037. Min Range: -6.1037

Max Act: 5.0384. Min Act: -0.0000

Data Index: 1583911 (Python Code)

Max Activating Token Index: 212

Text #4

Max Range: 6.1037. Min Range: -6.1037

Max Act: 5.0975. Min Act: -0.0000

Data Index: 1412797 (Python Code)

Max Activating Token Index: 623

Text #5

Max Range: 6.1037. Min Range: -6.1037

Max Act: 5.0843. Min Act: -0.0000

Data Index: 1553497 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.8706. Min Act: -0.0000

Data Index: 1457374 (Python Code)

Max Activating Token Index: 920

Text #7

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.7392. Min Act: -0.0000

Data Index: 1625676 (Python Code)

Max Activating Token Index: 842

Text #8

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.9097. Min Act: -0.0000

Data Index: 1549524 (Python Code)

Max Activating Token Index: 472

Text #9

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.6809. Min Act: -0.0000

Data Index: 1569042 (Python Code)

Max Activating Token Index: 751

Text #10

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.6509. Min Act: -0.0000

Data Index: 1477390 (Python Code)

Max Activating Token Index: 102

Text #11

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.6337. Min Act: -0.0000

Data Index: 1623404 (Python Code)

Max Activating Token Index: 388

Text #12

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.8194. Min Act: -0.0000

Data Index: 1523957 (Python Code)

Max Activating Token Index: 601

Text #13

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.6015. Min Act: -0.0000

Data Index: 1411211 (Python Code)

Max Activating Token Index: 997

Text #14

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.9109. Min Act: -0.0000

Data Index: 1587754 (Python Code)

Max Activating Token Index: 757

Text #15

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.7092. Min Act: -0.0000

Data Index: 1646316 (Python Code)

Max Activating Token Index: 8

Text #16

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.4878. Min Act: -0.0000

Data Index: 1531456 (Python Code)

Max Activating Token Index: 457

Text #17

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.6266. Min Act: -0.0000

Data Index: 1445281 (Python Code)

Max Activating Token Index: 292

Text #18

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.8136. Min Act: -0.0000

Data Index: 1377318 (Python Code)

Max Activating Token Index: 731

Text #19

Max Range: 6.1037. Min Range: -6.1037

Max Act: 4.5858. Min Act: -0.0000

Data Index: 1544932 (Python Code)

Max Activating Token Index: 670