Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 920 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1156. Min Act: -0.0005

Data Index: 193993 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0990. Min Act: -0.0005

Data Index: 1422435 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.1002. Min Act: -0.0005

Data Index: 1552063 (Python Code)

Max Activating Token Index: 850

Text #3

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0969. Min Act: -0.0005

Data Index: 1612982 (Python Code)

Max Activating Token Index: 965

Text #4

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0960. Min Act: -0.0005

Data Index: 1124198 (C4 (Web Text))

Max Activating Token Index: 721

Text #5

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0981. Min Act: -0.0005

Data Index: 223577 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0966. Min Act: -0.0005

Data Index: 912218 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0897. Min Act: -0.0005

Data Index: 1434077 (Python Code)

Max Activating Token Index: 1023

Text #8

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0905. Min Act: -0.0005

Data Index: 207591 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0916. Min Act: -0.0005

Data Index: 164320 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0908. Min Act: -0.0005

Data Index: 1235327 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0875. Min Act: -0.0005

Data Index: 282348 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0839. Min Act: -0.0005

Data Index: 548457 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0902. Min Act: -0.0005

Data Index: 198253 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0833. Min Act: -0.0005

Data Index: 1340313 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0884. Min Act: -0.0005

Data Index: 1144833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0902. Min Act: -0.0005

Data Index: 1190765 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0869. Min Act: -0.0005

Data Index: 1237746 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0869. Min Act: -0.0005

Data Index: 1140961 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.1156. Min Range: -0.1156

Max Act: 0.0845. Min Act: -0.0005

Data Index: 1025742 (C4 (Web Text))

Max Activating Token Index: 1023