Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3782 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1184. Min Act: -0.0002

Data Index: 580970 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1154. Min Act: -0.0002

Data Index: 62864 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1146. Min Act: -0.0002

Data Index: 676214 (C4 (Web Text))

Max Activating Token Index: 1016

Text #3

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1014. Min Act: -0.0001

Data Index: 521449 (C4 (Web Text))

Max Activating Token Index: 32

Text #4

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1604886 (Python Code)

Max Activating Token Index: 51

Text #5

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1581489 (Python Code)

Max Activating Token Index: 518

Text #6

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1030. Min Act: -0.0001

Data Index: 1559399 (Python Code)

Max Activating Token Index: 21

Text #7

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0941. Min Act: -0.0002

Data Index: 1021826 (C4 (Web Text))

Max Activating Token Index: 964

Text #8

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0973. Min Act: -0.0001

Data Index: 836059 (C4 (Web Text))

Max Activating Token Index: 885

Text #9

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1032936 (C4 (Web Text))

Max Activating Token Index: 809

Text #10

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1003. Min Act: -0.0001

Data Index: 1468137 (Python Code)

Max Activating Token Index: 15

Text #11

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0997. Min Act: -0.0001

Data Index: 170777 (C4 (Web Text))

Max Activating Token Index: 49

Text #12

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1022. Min Act: -0.0001

Data Index: 889374 (C4 (Web Text))

Max Activating Token Index: 372

Text #13

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0986. Min Act: -0.0002

Data Index: 89525 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1014. Min Act: -0.0001

Data Index: 208306 (C4 (Web Text))

Max Activating Token Index: 911

Text #15

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0966. Min Act: -0.0001

Data Index: 14436 (C4 (Web Text))

Max Activating Token Index: 664

Text #16

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.1004. Min Act: -0.0002

Data Index: 611169 (C4 (Web Text))

Max Activating Token Index: 638

Text #17

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0980. Min Act: -0.0001

Data Index: 225055 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0982. Min Act: -0.0002

Data Index: 349986 (C4 (Web Text))

Max Activating Token Index: 841

Text #19

Max Range: 0.1184. Min Range: -0.1184

Max Act: 0.0942. Min Act: -0.0002

Data Index: 274502 (C4 (Web Text))

Max Activating Token Index: 31