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

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

Neuron 825 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7569. Min Act: -0.0000

Data Index: 1259602 (C4 (Web Text))

Max Activating Token Index: 121

Text #1

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7447. Min Act: -0.0000

Data Index: 523475 (C4 (Web Text))

Max Activating Token Index: 106

Text #2

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7509. Min Act: -0.0000

Data Index: 847108 (C4 (Web Text))

Max Activating Token Index: 764

Text #3

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7786. Min Act: -0.0000

Data Index: 670036 (C4 (Web Text))

Max Activating Token Index: 44

Text #4

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7940. Min Act: -0.0000

Data Index: 1345808 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.7111. Min Act: -0.0000

Data Index: 371412 (C4 (Web Text))

Max Activating Token Index: 31

Text #6

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5844. Min Act: -0.0001

Data Index: 552702 (C4 (Web Text))

Max Activating Token Index: 403

Text #7

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5593. Min Act: -0.0000

Data Index: 806927 (C4 (Web Text))

Max Activating Token Index: 208

Text #8

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6430. Min Act: -0.0001

Data Index: 782302 (C4 (Web Text))

Max Activating Token Index: 38

Text #9

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.6015. Min Act: -0.0001

Data Index: 928808 (C4 (Web Text))

Max Activating Token Index: 658

Text #10

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5428. Min Act: -0.0000

Data Index: 469048 (C4 (Web Text))

Max Activating Token Index: 699

Text #11

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5917. Min Act: -0.0000

Data Index: 795767 (C4 (Web Text))

Max Activating Token Index: 105

Text #12

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5468. Min Act: -0.0001

Data Index: 244646 (C4 (Web Text))

Max Activating Token Index: 21

Text #13

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5435. Min Act: -0.0000

Data Index: 875505 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5700. Min Act: -0.0000

Data Index: 554624 (C4 (Web Text))

Max Activating Token Index: 101

Text #15

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5065. Min Act: -0.0000

Data Index: 26823 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5488. Min Act: -0.0000

Data Index: 887965 (C4 (Web Text))

Max Activating Token Index: 836

Text #17

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.5057. Min Act: -0.0001

Data Index: 137652 (C4 (Web Text))

Max Activating Token Index: 518

Text #18

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.4880. Min Act: -0.0000

Data Index: 1015390 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.7940. Min Range: -1.7940

Max Act: 1.4844. Min Act: -0.0000

Data Index: 1258955 (C4 (Web Text))

Max Activating Token Index: 35