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

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

Neuron 4032 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1409. Min Act: -0.0000

Data Index: 1645047 (Python Code)

Max Activating Token Index: 974

Text #1

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1291. Min Act: -0.0000

Data Index: 1567638 (Python Code)

Max Activating Token Index: 200

Text #2

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1161. Min Act: -0.0000

Data Index: 1461709 (Python Code)

Max Activating Token Index: 162

Text #3

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1095. Min Act: -0.0000

Data Index: 1373675 (Python Code)

Max Activating Token Index: 874

Text #4

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1035. Min Act: 0.0000

Data Index: 1451217 (Python Code)

Max Activating Token Index: 308

Text #5

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1653276 (Python Code)

Max Activating Token Index: 230

Text #6

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1053. Min Act: -0.0000

Data Index: 1490647 (Python Code)

Max Activating Token Index: 708

Text #7

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1057. Min Act: -0.0000

Data Index: 1521623 (Python Code)

Max Activating Token Index: 321

Text #8

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1366297 (Python Code)

Max Activating Token Index: 83

Text #9

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1051. Min Act: -0.0001

Data Index: 1616732 (Python Code)

Max Activating Token Index: 262

Text #10

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1059. Min Act: -0.0000

Data Index: 1653975 (Python Code)

Max Activating Token Index: 65

Text #11

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.1076. Min Act: -0.0000

Data Index: 1497693 (Python Code)

Max Activating Token Index: 248

Text #12

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0892. Min Act: -0.0000

Data Index: 1470896 (Python Code)

Max Activating Token Index: 317

Text #13

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1648390 (Python Code)

Max Activating Token Index: 52

Text #14

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1590179 (Python Code)

Max Activating Token Index: 206

Text #15

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1365610 (Python Code)

Max Activating Token Index: 57

Text #16

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0925. Min Act: -0.0000

Data Index: 1655972 (Python Code)

Max Activating Token Index: 172

Text #17

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0923. Min Act: -0.0000

Data Index: 1628819 (Python Code)

Max Activating Token Index: 189

Text #18

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1542988 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.1409. Min Range: -0.1409

Max Act: 0.0940. Min Act: -0.0000

Data Index: 1515393 (Python Code)

Max Activating Token Index: 87