Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 639 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: -0.0003

Data Index: 1552794 (Python Code)

Max Activating Token Index: 48

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1189. Min Act: -0.0003

Data Index: 1511061 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1192. Min Act: -0.0002

Data Index: 1538807 (Python Code)

Max Activating Token Index: 303

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1092. Min Act: -0.0003

Data Index: 1540309 (Python Code)

Max Activating Token Index: 997

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1121. Min Act: -0.0003

Data Index: 1542972 (Python Code)

Max Activating Token Index: 610

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1029. Min Act: -0.0003

Data Index: 1596672 (Python Code)

Max Activating Token Index: 17

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1054. Min Act: -0.0003

Data Index: 1398695 (Python Code)

Max Activating Token Index: 430

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1056. Min Act: -0.0004

Data Index: 1514978 (Python Code)

Max Activating Token Index: 445

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1042. Min Act: -0.0003

Data Index: 1617095 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1000. Min Act: -0.0003

Data Index: 1451078 (Python Code)

Max Activating Token Index: 586

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0949. Min Act: -0.0003

Data Index: 1529784 (Python Code)

Max Activating Token Index: 529

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1008. Min Act: -0.0003

Data Index: 1426860 (Python Code)

Max Activating Token Index: 707

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0971. Min Act: -0.0003

Data Index: 1633266 (Python Code)

Max Activating Token Index: 84

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0953. Min Act: -0.0003

Data Index: 1497880 (Python Code)

Max Activating Token Index: 122

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0986. Min Act: -0.0003

Data Index: 1563905 (Python Code)

Max Activating Token Index: 695

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1513258 (Python Code)

Max Activating Token Index: 964

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0968. Min Act: -0.0003

Data Index: 1638120 (Python Code)

Max Activating Token Index: 347

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0881. Min Act: -0.0003

Data Index: 1449520 (Python Code)

Max Activating Token Index: 505

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0972. Min Act: -0.0003

Data Index: 1465076 (Python Code)

Max Activating Token Index: 53

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0930. Min Act: -0.0003

Data Index: 1374586 (Python Code)

Max Activating Token Index: 673