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

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

Neuron 139 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.7630. Min Act: -0.0001

Data Index: 1298613 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 3.1647. Min Range: -3.1647

Max Act: 3.0208. Min Act: -0.0000

Data Index: 1343800 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.1647. Min Range: -3.1647

Max Act: 3.0158. Min Act: -0.0000

Data Index: 1017590 (C4 (Web Text))

Max Activating Token Index: 16

Text #3

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.7049. Min Act: -0.0001

Data Index: 598884 (C4 (Web Text))

Max Activating Token Index: 99

Text #4

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.8058. Min Act: -0.0001

Data Index: 1179145 (C4 (Web Text))

Max Activating Token Index: 565

Text #5

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.7575. Min Act: -0.0001

Data Index: 924681 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 3.1647. Min Range: -3.1647

Max Act: 3.0378. Min Act: -0.0001

Data Index: 200265 (C4 (Web Text))

Max Activating Token Index: 43

Text #7

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.7558. Min Act: -0.0001

Data Index: 1173768 (C4 (Web Text))

Max Activating Token Index: 109

Text #8

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.7476. Min Act: -0.0001

Data Index: 533604 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.8812. Min Act: -0.0001

Data Index: 1043937 (C4 (Web Text))

Max Activating Token Index: 667

Text #10

Max Range: 3.1647. Min Range: -3.1647

Max Act: 3.0338. Min Act: -0.0001

Data Index: 633353 (C4 (Web Text))

Max Activating Token Index: 24

Text #11

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.8970. Min Act: -0.0001

Data Index: 680039 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 3.1647. Min Range: -3.1647

Max Act: 3.0044. Min Act: -0.0001

Data Index: 437762 (C4 (Web Text))

Max Activating Token Index: 42

Text #13

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.7254. Min Act: -0.0001

Data Index: 1272302 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 3.1647. Min Range: -3.1647

Max Act: 3.1647. Min Act: -0.0001

Data Index: 1223817 (C4 (Web Text))

Max Activating Token Index: 165

Text #15

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.7216. Min Act: -0.0001

Data Index: 816693 (C4 (Web Text))

Max Activating Token Index: 26

Text #16

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.6702. Min Act: -0.0001

Data Index: 1333000 (C4 (Web Text))

Max Activating Token Index: 903

Text #17

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.6517. Min Act: -0.0001

Data Index: 537421 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.8006. Min Act: -0.0001

Data Index: 845186 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 3.1647. Min Range: -3.1647

Max Act: 2.6520. Min Act: -0.0001

Data Index: 853973 (C4 (Web Text))

Max Activating Token Index: 190