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

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

Neuron 4060 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1255. Min Range: -7.1255

Max Act: 7.1255. Min Act: -0.0000

Data Index: 139275 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 7.1255. Min Range: -7.1255

Max Act: 6.8607. Min Act: -0.0000

Data Index: 616408 (C4 (Web Text))

Max Activating Token Index: 86

Text #2

Max Range: 7.1255. Min Range: -7.1255

Max Act: 6.6846. Min Act: -0.0000

Data Index: 1241981 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 7.1255. Min Range: -7.1255

Max Act: 6.4777. Min Act: -0.0000

Data Index: 399160 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 7.1255. Min Range: -7.1255

Max Act: 6.1299. Min Act: -0.0000

Data Index: 856201 (C4 (Web Text))

Max Activating Token Index: 555

Text #5

Max Range: 7.1255. Min Range: -7.1255

Max Act: 6.3204. Min Act: -0.0000

Data Index: 230299 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.8018. Min Act: -0.0000

Data Index: 953829 (C4 (Web Text))

Max Activating Token Index: 815

Text #7

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.9970. Min Act: -0.0000

Data Index: 943580 (C4 (Web Text))

Max Activating Token Index: 73

Text #8

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.7914. Min Act: -0.0000

Data Index: 1225352 (C4 (Web Text))

Max Activating Token Index: 57

Text #9

Max Range: 7.1255. Min Range: -7.1255

Max Act: 6.0997. Min Act: -0.0000

Data Index: 1133006 (C4 (Web Text))

Max Activating Token Index: 85

Text #10

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.9141. Min Act: -0.0000

Data Index: 371049 (C4 (Web Text))

Max Activating Token Index: 73

Text #11

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.8635. Min Act: -0.0000

Data Index: 919722 (C4 (Web Text))

Max Activating Token Index: 225

Text #12

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.7147. Min Act: -0.0000

Data Index: 94398 (C4 (Web Text))

Max Activating Token Index: 91

Text #13

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.4989. Min Act: -0.0000

Data Index: 1076210 (C4 (Web Text))

Max Activating Token Index: 119

Text #14

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.4927. Min Act: -0.0000

Data Index: 203530 (C4 (Web Text))

Max Activating Token Index: 90

Text #15

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.4531. Min Act: -0.0000

Data Index: 215536 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.2679. Min Act: -0.0000

Data Index: 1162202 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.2616. Min Act: -0.0000

Data Index: 960061 (C4 (Web Text))

Max Activating Token Index: 247

Text #18

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.5812. Min Act: -0.0000

Data Index: 82354 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 7.1255. Min Range: -7.1255

Max Act: 5.1819. Min Act: -0.0000

Data Index: 684855 (C4 (Web Text))

Max Activating Token Index: 156