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

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

Neuron 2845 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2144. Min Range: -3.2144

Max Act: 3.2144. Min Act: -0.0000

Data Index: 1619178 (Python Code)

Max Activating Token Index: 20

Text #1

Max Range: 3.2144. Min Range: -3.2144

Max Act: 3.0986. Min Act: -0.0000

Data Index: 1379553 (Python Code)

Max Activating Token Index: 94

Text #2

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.6447. Min Act: -0.0000

Data Index: 1488697 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.8029. Min Act: -0.0000

Data Index: 1656911 (Python Code)

Max Activating Token Index: 350

Text #4

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.7620. Min Act: -0.0000

Data Index: 1415043 (Python Code)

Max Activating Token Index: 35

Text #5

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.7112. Min Act: -0.0000

Data Index: 1390702 (Python Code)

Max Activating Token Index: 303

Text #6

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.3593. Min Act: -0.0000

Data Index: 1483215 (Python Code)

Max Activating Token Index: 1012

Text #7

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.4743. Min Act: -0.0000

Data Index: 1444960 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.4610. Min Act: -0.0000

Data Index: 1562481 (Python Code)

Max Activating Token Index: 35

Text #9

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.4527. Min Act: -0.0000

Data Index: 939159 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.5435. Min Act: -0.0000

Data Index: 1532997 (Python Code)

Max Activating Token Index: 166

Text #11

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.3915. Min Act: -0.0000

Data Index: 1447541 (Python Code)

Max Activating Token Index: 169

Text #12

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.4019. Min Act: -0.0000

Data Index: 1553835 (Python Code)

Max Activating Token Index: 208

Text #13

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.3562. Min Act: -0.0000

Data Index: 1635243 (Python Code)

Max Activating Token Index: 427

Text #14

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.3561. Min Act: -0.0000

Data Index: 1482509 (Python Code)

Max Activating Token Index: 743

Text #15

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.3374. Min Act: -0.0000

Data Index: 1451004 (Python Code)

Max Activating Token Index: 84

Text #16

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.4245. Min Act: -0.0000

Data Index: 1163272 (C4 (Web Text))

Max Activating Token Index: 542

Text #17

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.3024. Min Act: -0.0000

Data Index: 1480156 (Python Code)

Max Activating Token Index: 1014

Text #18

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.4077. Min Act: -0.0000

Data Index: 1648274 (Python Code)

Max Activating Token Index: 185

Text #19

Max Range: 3.2144. Min Range: -3.2144

Max Act: 2.2800. Min Act: -0.0000

Data Index: 1615255 (Python Code)

Max Activating Token Index: 46