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

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

Neuron 3583 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1934. Min Act: -0.0000

Data Index: 554364 (C4 (Web Text))

Max Activating Token Index: 52

Text #1

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1911. Min Act: -0.0000

Data Index: 119324 (C4 (Web Text))

Max Activating Token Index: 426

Text #2

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1637. Min Act: -0.0000

Data Index: 1110206 (C4 (Web Text))

Max Activating Token Index: 39

Text #3

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1551982 (Python Code)

Max Activating Token Index: 946

Text #4

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1660. Min Act: -0.0000

Data Index: 506845 (C4 (Web Text))

Max Activating Token Index: 105

Text #5

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1540. Min Act: -0.0000

Data Index: 733871 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1647894 (Python Code)

Max Activating Token Index: 489

Text #7

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1485. Min Act: -0.0000

Data Index: 331325 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1170415 (C4 (Web Text))

Max Activating Token Index: 81

Text #9

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1479. Min Act: -0.0000

Data Index: 1063622 (C4 (Web Text))

Max Activating Token Index: 35

Text #10

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1572. Min Act: -0.0000

Data Index: 1087996 (C4 (Web Text))

Max Activating Token Index: 836

Text #11

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1661. Min Act: -0.0000

Data Index: 624899 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1363. Min Act: -0.0000

Data Index: 1580201 (Python Code)

Max Activating Token Index: 873

Text #13

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1532. Min Act: -0.0000

Data Index: 1320868 (C4 (Web Text))

Max Activating Token Index: 108

Text #14

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1438. Min Act: -0.0000

Data Index: 189318 (C4 (Web Text))

Max Activating Token Index: 842

Text #15

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1339. Min Act: -0.0000

Data Index: 668915 (C4 (Web Text))

Max Activating Token Index: 979

Text #16

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1274. Min Act: -0.0000

Data Index: 873151 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1346. Min Act: -0.0000

Data Index: 856908 (C4 (Web Text))

Max Activating Token Index: 216

Text #18

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1323. Min Act: -0.0000

Data Index: 290356 (C4 (Web Text))

Max Activating Token Index: 103

Text #19

Max Range: 0.1934. Min Range: -0.1934

Max Act: 0.1281. Min Act: -0.0000

Data Index: 1019756 (C4 (Web Text))

Max Activating Token Index: 909