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

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

Neuron 5560 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.6170. Min Act: -0.0001

Data Index: 1195973 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5830. Min Act: -0.0001

Data Index: 1161706 (C4 (Web Text))

Max Activating Token Index: 50

Text #2

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5277. Min Act: -0.0001

Data Index: 1093596 (C4 (Web Text))

Max Activating Token Index: 859

Text #3

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5113. Min Act: -0.0001

Data Index: 1060874 (C4 (Web Text))

Max Activating Token Index: 232

Text #4

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5655. Min Act: -0.0001

Data Index: 657614 (C4 (Web Text))

Max Activating Token Index: 7

Text #5

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5770. Min Act: -0.0001

Data Index: 1204545 (C4 (Web Text))

Max Activating Token Index: 962

Text #6

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4954. Min Act: -0.0001

Data Index: 757665 (C4 (Web Text))

Max Activating Token Index: 32

Text #7

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5090. Min Act: -0.0001

Data Index: 498289 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5378. Min Act: -0.0001

Data Index: 61872 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5453. Min Act: -0.0001

Data Index: 618916 (C4 (Web Text))

Max Activating Token Index: 321

Text #10

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5446. Min Act: -0.0001

Data Index: 783277 (C4 (Web Text))

Max Activating Token Index: 46

Text #11

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4997. Min Act: -0.0001

Data Index: 404328 (C4 (Web Text))

Max Activating Token Index: 732

Text #12

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5080. Min Act: -0.0001

Data Index: 142064 (C4 (Web Text))

Max Activating Token Index: 893

Text #13

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5190. Min Act: -0.0001

Data Index: 406898 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4849. Min Act: -0.0001

Data Index: 731389 (C4 (Web Text))

Max Activating Token Index: 251

Text #15

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4973. Min Act: -0.0001

Data Index: 755327 (C4 (Web Text))

Max Activating Token Index: 838

Text #16

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5031. Min Act: -0.0001

Data Index: 1139685 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5501. Min Act: -0.0001

Data Index: 985224 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.4862. Min Act: -0.0001

Data Index: 425966 (C4 (Web Text))

Max Activating Token Index: 406

Text #19

Max Range: 0.6170. Min Range: -0.6170

Max Act: 0.5035. Min Act: -0.0001

Data Index: 1032742 (C4 (Web Text))

Max Activating Token Index: 684