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

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

Neuron 1453 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1203. Min Act: -0.0002

Data Index: 346440 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1125. Min Act: -0.0003

Data Index: 1155774 (C4 (Web Text))

Max Activating Token Index: 55

Text #2

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1087. Min Act: -0.0003

Data Index: 853920 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1068. Min Act: -0.0002

Data Index: 527959 (C4 (Web Text))

Max Activating Token Index: 250

Text #4

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1071. Min Act: -0.0002

Data Index: 1184996 (C4 (Web Text))

Max Activating Token Index: 285

Text #5

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1057. Min Act: -0.0002

Data Index: 574740 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1042. Min Act: -0.0003

Data Index: 1264242 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1014. Min Act: -0.0002

Data Index: 809246 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1028. Min Act: -0.0002

Data Index: 1351477 (C4 (Web Text))

Max Activating Token Index: 28

Text #9

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0997. Min Act: -0.0002

Data Index: 1202754 (C4 (Web Text))

Max Activating Token Index: 252

Text #10

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0989. Min Act: -0.0002

Data Index: 1258653 (C4 (Web Text))

Max Activating Token Index: 266

Text #11

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1001. Min Act: -0.0002

Data Index: 1240923 (C4 (Web Text))

Max Activating Token Index: 574

Text #12

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1004. Min Act: -0.0002

Data Index: 496386 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1220512 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.1005. Min Act: -0.0002

Data Index: 271791 (C4 (Web Text))

Max Activating Token Index: 383

Text #15

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0986. Min Act: -0.0002

Data Index: 44320 (C4 (Web Text))

Max Activating Token Index: 15

Text #16

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0975. Min Act: -0.0002

Data Index: 750814 (C4 (Web Text))

Max Activating Token Index: 584

Text #17

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0976. Min Act: -0.0002

Data Index: 442023 (C4 (Web Text))

Max Activating Token Index: 516

Text #18

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0968. Min Act: -0.0002

Data Index: 499981 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.1203. Min Range: -0.1203

Max Act: 0.0966. Min Act: -0.0002

Data Index: 818282 (C4 (Web Text))

Max Activating Token Index: 95