Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 749 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.8741. Min Act: -0.0000

Data Index: 1386374 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.7924. Min Act: -0.0000

Data Index: 1434405 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.7296. Min Act: -0.0000

Data Index: 1598442 (Python Code)

Max Activating Token Index: 146

Text #3

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.7208. Min Act: -0.0000

Data Index: 1476524 (Python Code)

Max Activating Token Index: 91

Text #4

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.7201. Min Act: -0.0000

Data Index: 1534725 (Python Code)

Max Activating Token Index: 149

Text #5

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6929. Min Act: -0.0000

Data Index: 1584555 (Python Code)

Max Activating Token Index: 47

Text #6

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1647633 (Python Code)

Max Activating Token Index: 75

Text #7

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1508844 (Python Code)

Max Activating Token Index: 84

Text #8

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1409210 (Python Code)

Max Activating Token Index: 898

Text #9

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1612504 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1362063 (Python Code)

Max Activating Token Index: 96

Text #11

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6609. Min Act: -0.0000

Data Index: 1596570 (Python Code)

Max Activating Token Index: 59

Text #12

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5866. Min Act: -0.0000

Data Index: 1514644 (Python Code)

Max Activating Token Index: 193

Text #13

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.6021. Min Act: -0.0000

Data Index: 1365616 (Python Code)

Max Activating Token Index: 81

Text #14

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1433252 (Python Code)

Max Activating Token Index: 90

Text #15

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5721. Min Act: -0.0000

Data Index: 1424390 (Python Code)

Max Activating Token Index: 179

Text #16

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1403053 (Python Code)

Max Activating Token Index: 100

Text #17

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1463478 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1395300 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 0.8741. Min Range: -0.8741

Max Act: 0.5026. Min Act: -0.0000

Data Index: 1397114 (Python Code)

Max Activating Token Index: 749