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

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

Neuron 62 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1457984 (Python Code)

Max Activating Token Index: 798

Text #1

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1079. Min Act: -0.0001

Data Index: 1526982 (Python Code)

Max Activating Token Index: 983

Text #2

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1655726 (Python Code)

Max Activating Token Index: 235

Text #3

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1150. Min Act: -0.0001

Data Index: 1368508 (Python Code)

Max Activating Token Index: 699

Text #4

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1608609 (Python Code)

Max Activating Token Index: 127

Text #5

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1459190 (Python Code)

Max Activating Token Index: 155

Text #6

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1397183 (Python Code)

Max Activating Token Index: 874

Text #7

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1095. Min Act: -0.0001

Data Index: 1526697 (Python Code)

Max Activating Token Index: 95

Text #8

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1022. Min Act: -0.0001

Data Index: 1528703 (Python Code)

Max Activating Token Index: 492

Text #9

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1509183 (Python Code)

Max Activating Token Index: 505

Text #10

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1499716 (Python Code)

Max Activating Token Index: 601

Text #11

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1512676 (Python Code)

Max Activating Token Index: 123

Text #12

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1652294 (Python Code)

Max Activating Token Index: 95

Text #13

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1019. Min Act: -0.0001

Data Index: 1629776 (Python Code)

Max Activating Token Index: 105

Text #14

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1531153 (Python Code)

Max Activating Token Index: 82

Text #15

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1047. Min Act: -0.0001

Data Index: 1424343 (Python Code)

Max Activating Token Index: 675

Text #16

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1008. Min Act: -0.0001

Data Index: 1582155 (Python Code)

Max Activating Token Index: 101

Text #17

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1043. Min Act: -0.0001

Data Index: 1475966 (Python Code)

Max Activating Token Index: 423

Text #18

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.1044. Min Act: -0.0001

Data Index: 1639806 (Python Code)

Max Activating Token Index: 532

Text #19

Max Range: 0.1263. Min Range: -0.1263

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1550472 (Python Code)

Max Activating Token Index: 111