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

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

Neuron 450 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8778. Min Act: -0.0001

Data Index: 1205333 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8525. Min Act: -0.0001

Data Index: 1265684 (C4 (Web Text))

Max Activating Token Index: 77

Text #2

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7384. Min Act: -0.0001

Data Index: 147207 (C4 (Web Text))

Max Activating Token Index: 172

Text #3

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7732. Min Act: -0.0001

Data Index: 853729 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8109. Min Act: -0.0001

Data Index: 1315221 (C4 (Web Text))

Max Activating Token Index: 81

Text #5

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7278. Min Act: -0.0001

Data Index: 612881 (C4 (Web Text))

Max Activating Token Index: 273

Text #6

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8058. Min Act: -0.0001

Data Index: 279073 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8272. Min Act: -0.0001

Data Index: 515353 (C4 (Web Text))

Max Activating Token Index: 102

Text #8

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8159. Min Act: -0.0001

Data Index: 1130407 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7872. Min Act: -0.0001

Data Index: 1048486 (C4 (Web Text))

Max Activating Token Index: 130

Text #10

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7781. Min Act: -0.0001

Data Index: 982220 (C4 (Web Text))

Max Activating Token Index: 68

Text #11

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7625. Min Act: -0.0001

Data Index: 875073 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7679. Min Act: -0.0001

Data Index: 46589 (C4 (Web Text))

Max Activating Token Index: 60

Text #13

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7679. Min Act: -0.0001

Data Index: 1259218 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7303. Min Act: -0.0001

Data Index: 733265 (C4 (Web Text))

Max Activating Token Index: 218

Text #15

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8126. Min Act: -0.0001

Data Index: 1285854 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7179. Min Act: -0.0001

Data Index: 523898 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.8275. Min Act: -0.0001

Data Index: 403274 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1276576 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.8778. Min Range: -0.8778

Max Act: 0.6591. Min Act: -0.0001

Data Index: 1275510 (C4 (Web Text))

Max Activating Token Index: 136