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

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

Neuron 1185 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1661. Min Act: -0.0000

Data Index: 614438 (C4 (Web Text))

Max Activating Token Index: 17

Text #1

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1598. Min Act: -0.0000

Data Index: 518197 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1438. Min Act: -0.0000

Data Index: 205683 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1250. Min Act: -0.0000

Data Index: 1053101 (C4 (Web Text))

Max Activating Token Index: 844

Text #4

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1286. Min Act: -0.0000

Data Index: 881992 (C4 (Web Text))

Max Activating Token Index: 387

Text #5

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1257. Min Act: -0.0000

Data Index: 1234567 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1255. Min Act: -0.0000

Data Index: 990191 (C4 (Web Text))

Max Activating Token Index: 285

Text #7

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1139. Min Act: -0.0000

Data Index: 817850 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1090. Min Act: -0.0000

Data Index: 962679 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1051. Min Act: -0.0000

Data Index: 972710 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1116. Min Act: -0.0000

Data Index: 754568 (C4 (Web Text))

Max Activating Token Index: 17

Text #11

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1107. Min Act: -0.0000

Data Index: 36397 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1073. Min Act: -0.0000

Data Index: 842425 (C4 (Web Text))

Max Activating Token Index: 305

Text #13

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1056. Min Act: -0.0000

Data Index: 127578 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1046. Min Act: -0.0000

Data Index: 943636 (C4 (Web Text))

Max Activating Token Index: 6

Text #15

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1041. Min Act: -0.0000

Data Index: 1083069 (C4 (Web Text))

Max Activating Token Index: 408

Text #16

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1039. Min Act: -0.0000

Data Index: 850671 (C4 (Web Text))

Max Activating Token Index: 512

Text #17

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1065. Min Act: -0.0000

Data Index: 86580 (C4 (Web Text))

Max Activating Token Index: 693

Text #18

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1063. Min Act: -0.0000

Data Index: 1593772 (Python Code)

Max Activating Token Index: 14

Text #19

Max Range: 0.1661. Min Range: -0.1661

Max Act: 0.1176. Min Act: -0.0000

Data Index: 778035 (C4 (Web Text))

Max Activating Token Index: 531