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

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

Neuron 2528 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1614078 (Python Code)

Max Activating Token Index: 204

Text #1

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.1026. Min Act: -0.0002

Data Index: 1424641 (Python Code)

Max Activating Token Index: 366

Text #2

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0963. Min Act: -0.0002

Data Index: 1569695 (Python Code)

Max Activating Token Index: 420

Text #3

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1406163 (Python Code)

Max Activating Token Index: 725

Text #4

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0936. Min Act: -0.0002

Data Index: 1388544 (Python Code)

Max Activating Token Index: 181

Text #5

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1539260 (Python Code)

Max Activating Token Index: 157

Text #6

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0952. Min Act: -0.0002

Data Index: 1568952 (Python Code)

Max Activating Token Index: 142

Text #7

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0847. Min Act: -0.0002

Data Index: 1424009 (Python Code)

Max Activating Token Index: 181

Text #8

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0943. Min Act: -0.0002

Data Index: 1484934 (Python Code)

Max Activating Token Index: 837

Text #9

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0894. Min Act: -0.0002

Data Index: 1492904 (Python Code)

Max Activating Token Index: 109

Text #10

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0930. Min Act: -0.0002

Data Index: 1371673 (Python Code)

Max Activating Token Index: 140

Text #11

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0914. Min Act: -0.0002

Data Index: 1487847 (Python Code)

Max Activating Token Index: 188

Text #12

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0848. Min Act: -0.0002

Data Index: 1438971 (Python Code)

Max Activating Token Index: 127

Text #13

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0881. Min Act: -0.0002

Data Index: 1402229 (Python Code)

Max Activating Token Index: 324

Text #14

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0829. Min Act: -0.0002

Data Index: 1430623 (Python Code)

Max Activating Token Index: 581

Text #15

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0866. Min Act: -0.0002

Data Index: 1476721 (Python Code)

Max Activating Token Index: 209

Text #16

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0854. Min Act: -0.0002

Data Index: 1367751 (Python Code)

Max Activating Token Index: 830

Text #17

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1655447 (Python Code)

Max Activating Token Index: 684

Text #18

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0951. Min Act: -0.0002

Data Index: 1612869 (Python Code)

Max Activating Token Index: 726

Text #19

Max Range: 0.1053. Min Range: -0.1053

Max Act: 0.0857. Min Act: -0.0002

Data Index: 1542895 (Python Code)

Max Activating Token Index: 478