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

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

Neuron 1251 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: 2.2115. Min Range: -2.2115

Max Act: 2.2115. Min Act: -0.0001

Data Index: 240925 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 2.2115. Min Range: -2.2115

Max Act: 2.0811. Min Act: -0.0000

Data Index: 316364 (C4 (Web Text))

Max Activating Token Index: 782

Text #2

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.9728. Min Act: -0.0000

Data Index: 276399 (C4 (Web Text))

Max Activating Token Index: 656

Text #3

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.9661. Min Act: -0.0000

Data Index: 634989 (C4 (Web Text))

Max Activating Token Index: 205

Text #4

Max Range: 2.2115. Min Range: -2.2115

Max Act: 2.0267. Min Act: -0.0000

Data Index: 410099 (C4 (Web Text))

Max Activating Token Index: 14

Text #5

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.9013. Min Act: -0.0001

Data Index: 108179 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.8569. Min Act: -0.0000

Data Index: 543197 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 2.2115. Min Range: -2.2115

Max Act: 2.0280. Min Act: -0.0000

Data Index: 626957 (C4 (Web Text))

Max Activating Token Index: 355

Text #8

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.7775. Min Act: -0.0000

Data Index: 233811 (C4 (Web Text))

Max Activating Token Index: 607

Text #9

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.7241. Min Act: -0.0001

Data Index: 1295492 (C4 (Web Text))

Max Activating Token Index: 793

Text #10

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.6015. Min Act: -0.0001

Data Index: 1310854 (C4 (Web Text))

Max Activating Token Index: 179

Text #11

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.6824. Min Act: -0.0001

Data Index: 1098604 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 2.2115. Min Range: -2.2115

Max Act: 2.0014. Min Act: -0.0001

Data Index: 1024457 (C4 (Web Text))

Max Activating Token Index: 950

Text #13

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.8861. Min Act: -0.0000

Data Index: 1023282 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.6525. Min Act: -0.0000

Data Index: 1021950 (C4 (Web Text))

Max Activating Token Index: 669

Text #15

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.8435. Min Act: -0.0000

Data Index: 832177 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.7466. Min Act: -0.0000

Data Index: 1145120 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.7281. Min Act: -0.0000

Data Index: 1032560 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.6546. Min Act: -0.0000

Data Index: 1290352 (C4 (Web Text))

Max Activating Token Index: 399

Text #19

Max Range: 2.2115. Min Range: -2.2115

Max Act: 1.8309. Min Act: -0.0000

Data Index: 214812 (C4 (Web Text))

Max Activating Token Index: 506