Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2552 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.2360. Min Act: -0.0001

Data Index: 1594801 (Python Code)

Max Activating Token Index: 102

Text #1

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1946. Min Act: -0.0001

Data Index: 1392154 (Python Code)

Max Activating Token Index: 788

Text #2

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1642. Min Act: -0.0001

Data Index: 1607722 (Python Code)

Max Activating Token Index: 718

Text #3

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1617756 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1561. Min Act: -0.0001

Data Index: 1419573 (Python Code)

Max Activating Token Index: 406

Text #5

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1604. Min Act: -0.0001

Data Index: 1640838 (Python Code)

Max Activating Token Index: 120

Text #6

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1281. Min Act: -0.0001

Data Index: 369567 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1411. Min Act: -0.0001

Data Index: 1612217 (Python Code)

Max Activating Token Index: 556

Text #8

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1391. Min Act: -0.0001

Data Index: 553941 (C4 (Web Text))

Max Activating Token Index: 374

Text #9

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1332. Min Act: -0.0001

Data Index: 1409888 (Python Code)

Max Activating Token Index: 48

Text #10

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1238. Min Act: -0.0001

Data Index: 473440 (C4 (Web Text))

Max Activating Token Index: 796

Text #11

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1283. Min Act: -0.0001

Data Index: 670296 (C4 (Web Text))

Max Activating Token Index: 844

Text #12

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1312. Min Act: -0.0001

Data Index: 1417635 (Python Code)

Max Activating Token Index: 388

Text #13

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1215. Min Act: -0.0001

Data Index: 996208 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1237. Min Act: -0.0001

Data Index: 470707 (C4 (Web Text))

Max Activating Token Index: 906

Text #15

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1066. Min Act: -0.0001

Data Index: 1547969 (Python Code)

Max Activating Token Index: 669

Text #16

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1205. Min Act: -0.0001

Data Index: 1545551 (Python Code)

Max Activating Token Index: 177

Text #17

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1492072 (Python Code)

Max Activating Token Index: 708

Text #18

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1206. Min Act: -0.0001

Data Index: 149935 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 0.2360. Min Range: -0.2360

Max Act: 0.1236. Min Act: -0.0001

Data Index: 1394745 (Python Code)

Max Activating Token Index: 822