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

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

Neuron 690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1275. Min Act: -0.0001

Data Index: 1466134 (Python Code)

Max Activating Token Index: 962

Text #1

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1203. Min Act: -0.0000

Data Index: 1361983 (Python Code)

Max Activating Token Index: 126

Text #2

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1147. Min Act: -0.0000

Data Index: 1490031 (Python Code)

Max Activating Token Index: 258

Text #3

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1092. Min Act: -0.0001

Data Index: 93273 (C4 (Web Text))

Max Activating Token Index: 107

Text #4

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1090. Min Act: -0.0001

Data Index: 1425985 (Python Code)

Max Activating Token Index: 706

Text #5

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1624754 (Python Code)

Max Activating Token Index: 174

Text #6

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1055. Min Act: -0.0001

Data Index: 1395419 (Python Code)

Max Activating Token Index: 309

Text #7

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1096. Min Act: -0.0000

Data Index: 1402288 (Python Code)

Max Activating Token Index: 1000

Text #8

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1484434 (Python Code)

Max Activating Token Index: 1002

Text #9

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1052. Min Act: -0.0000

Data Index: 1580677 (Python Code)

Max Activating Token Index: 275

Text #10

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1052. Min Act: -0.0001

Data Index: 1651354 (Python Code)

Max Activating Token Index: 714

Text #11

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1568404 (Python Code)

Max Activating Token Index: 830

Text #12

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1042. Min Act: -0.0001

Data Index: 1655103 (Python Code)

Max Activating Token Index: 229

Text #13

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0967. Min Act: -0.0001

Data Index: 1557758 (Python Code)

Max Activating Token Index: 219

Text #14

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1423612 (Python Code)

Max Activating Token Index: 390

Text #15

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1040. Min Act: -0.0001

Data Index: 1522413 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1071. Min Act: -0.0001

Data Index: 1548554 (Python Code)

Max Activating Token Index: 954

Text #17

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0993. Min Act: -0.0000

Data Index: 1469908 (Python Code)

Max Activating Token Index: 295

Text #18

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1496434 (Python Code)

Max Activating Token Index: 512

Text #19

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1464664 (Python Code)

Max Activating Token Index: 59