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

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

Neuron 4207 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.3122. Min Act: -0.0000

Data Index: 1467724 (Python Code)

Max Activating Token Index: 327

Text #1

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.2954. Min Act: -0.0000

Data Index: 1401456 (Python Code)

Max Activating Token Index: 77

Text #2

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1626067 (Python Code)

Max Activating Token Index: 880

Text #3

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.0590. Min Act: -0.0000

Data Index: 1392414 (Python Code)

Max Activating Token Index: 70

Text #4

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1629481 (Python Code)

Max Activating Token Index: 582

Text #5

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.1100. Min Act: -0.0000

Data Index: 1557842 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1531436 (Python Code)

Max Activating Token Index: 991

Text #7

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.0601. Min Act: -0.0000

Data Index: 1465832 (Python Code)

Max Activating Token Index: 671

Text #8

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.9678. Min Act: -0.0000

Data Index: 501188 (C4 (Web Text))

Max Activating Token Index: 50

Text #9

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.9425. Min Act: -0.0000

Data Index: 1174911 (C4 (Web Text))

Max Activating Token Index: 790

Text #10

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.9614. Min Act: -0.0000

Data Index: 1486894 (Python Code)

Max Activating Token Index: 773

Text #11

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1554404 (Python Code)

Max Activating Token Index: 500

Text #12

Max Range: 1.3122. Min Range: -1.3122

Max Act: 1.0095. Min Act: -0.0000

Data Index: 1443956 (Python Code)

Max Activating Token Index: 1017

Text #13

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.9290. Min Act: -0.0000

Data Index: 1429373 (Python Code)

Max Activating Token Index: 112

Text #14

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.9239. Min Act: -0.0000

Data Index: 1602213 (Python Code)

Max Activating Token Index: 511

Text #15

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.8977. Min Act: -0.0000

Data Index: 1597652 (Python Code)

Max Activating Token Index: 496

Text #16

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.8892. Min Act: -0.0000

Data Index: 1652922 (Python Code)

Max Activating Token Index: 504

Text #17

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1446094 (Python Code)

Max Activating Token Index: 187

Text #18

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.8682. Min Act: -0.0000

Data Index: 1495545 (Python Code)

Max Activating Token Index: 594

Text #19

Max Range: 1.3122. Min Range: -1.3122

Max Act: 0.8815. Min Act: -0.0000

Data Index: 1542636 (Python Code)

Max Activating Token Index: 392