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

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

Neuron 367 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.2002. Min Act: -0.0001

Data Index: 1395557 (Python Code)

Max Activating Token Index: 255

Text #1

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1851. Min Act: -0.0001

Data Index: 1372547 (Python Code)

Max Activating Token Index: 692

Text #2

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1634. Min Act: -0.0001

Data Index: 1562534 (Python Code)

Max Activating Token Index: 1000

Text #3

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1402805 (Python Code)

Max Activating Token Index: 326

Text #4

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1473303 (Python Code)

Max Activating Token Index: 232

Text #5

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1371622 (Python Code)

Max Activating Token Index: 11

Text #6

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1406382 (Python Code)

Max Activating Token Index: 292

Text #7

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1560. Min Act: -0.0000

Data Index: 1590351 (Python Code)

Max Activating Token Index: 749

Text #8

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1509. Min Act: -0.0001

Data Index: 1418687 (Python Code)

Max Activating Token Index: 255

Text #9

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1192. Min Act: -0.0000

Data Index: 1391560 (Python Code)

Max Activating Token Index: 615

Text #10

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1464. Min Act: -0.0001

Data Index: 1464577 (Python Code)

Max Activating Token Index: 734

Text #11

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1562304 (Python Code)

Max Activating Token Index: 117

Text #12

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1429. Min Act: -0.0000

Data Index: 1439278 (Python Code)

Max Activating Token Index: 261

Text #13

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1266. Min Act: -0.0001

Data Index: 1432153 (Python Code)

Max Activating Token Index: 53

Text #14

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1233. Min Act: -0.0001

Data Index: 1541108 (Python Code)

Max Activating Token Index: 749

Text #15

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1237. Min Act: -0.0001

Data Index: 1504870 (Python Code)

Max Activating Token Index: 215

Text #16

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1059. Min Act: -0.0001

Data Index: 1598968 (Python Code)

Max Activating Token Index: 209

Text #17

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1270. Min Act: -0.0001

Data Index: 1492748 (Python Code)

Max Activating Token Index: 101

Text #18

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1170. Min Act: -0.0000

Data Index: 1614003 (Python Code)

Max Activating Token Index: 807

Text #19

Max Range: 0.2002. Min Range: -0.2002

Max Act: 0.1217. Min Act: -0.0001

Data Index: 1423296 (Python Code)

Max Activating Token Index: 19