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

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

Neuron 1197 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: 2.7375. Min Range: -2.7375

Max Act: 2.7375. Min Act: -0.0000

Data Index: 416984 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.6018. Min Act: -0.0000

Data Index: 1270026 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.4671. Min Act: -0.0000

Data Index: 879349 (C4 (Web Text))

Max Activating Token Index: 204

Text #3

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.4004. Min Act: -0.0000

Data Index: 1090889 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.2694. Min Act: -0.0000

Data Index: 816723 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.1436. Min Act: -0.0001

Data Index: 404134 (C4 (Web Text))

Max Activating Token Index: 574

Text #6

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.2895. Min Act: -0.0000

Data Index: 1009860 (C4 (Web Text))

Max Activating Token Index: 177

Text #7

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.0645. Min Act: -0.0001

Data Index: 202487 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.2380. Min Act: -0.0000

Data Index: 865358 (C4 (Web Text))

Max Activating Token Index: 274

Text #9

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.2167. Min Act: -0.0001

Data Index: 645939 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 2.7375. Min Range: -2.7375

Max Act: 1.9599. Min Act: -0.0000

Data Index: 891478 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 2.7375. Min Range: -2.7375

Max Act: 1.9374. Min Act: -0.0001

Data Index: 311121 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 2.7375. Min Range: -2.7375

Max Act: 1.8450. Min Act: -0.0001

Data Index: 1022853 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.0335. Min Act: -0.0001

Data Index: 891960 (C4 (Web Text))

Max Activating Token Index: 123

Text #14

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.1242. Min Act: -0.0000

Data Index: 24776 (C4 (Web Text))

Max Activating Token Index: 255

Text #15

Max Range: 2.7375. Min Range: -2.7375

Max Act: 1.9267. Min Act: -0.0000

Data Index: 119208 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 2.7375. Min Range: -2.7375

Max Act: 1.8803. Min Act: -0.0001

Data Index: 1325992 (C4 (Web Text))

Max Activating Token Index: 979

Text #17

Max Range: 2.7375. Min Range: -2.7375

Max Act: 1.9580. Min Act: -0.0001

Data Index: 1020752 (C4 (Web Text))

Max Activating Token Index: 570

Text #18

Max Range: 2.7375. Min Range: -2.7375

Max Act: 2.0233. Min Act: -0.0000

Data Index: 233632 (C4 (Web Text))

Max Activating Token Index: 671

Text #19

Max Range: 2.7375. Min Range: -2.7375

Max Act: 1.9984. Min Act: -0.0001

Data Index: 17312 (C4 (Web Text))

Max Activating Token Index: 874