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

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

Neuron 4656 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1299318 (C4 (Web Text))

Max Activating Token Index: 821

Text #1

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1142. Min Act: -0.0001

Data Index: 307436 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1203653 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1098. Min Act: -0.0001

Data Index: 861206 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1070. Min Act: -0.0001

Data Index: 826878 (C4 (Web Text))

Max Activating Token Index: 941

Text #5

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1070. Min Act: -0.0001

Data Index: 1024368 (C4 (Web Text))

Max Activating Token Index: 250

Text #6

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1069. Min Act: -0.0001

Data Index: 725932 (C4 (Web Text))

Max Activating Token Index: 485

Text #7

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1249406 (C4 (Web Text))

Max Activating Token Index: 20

Text #8

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1028. Min Act: -0.0001

Data Index: 586677 (C4 (Web Text))

Max Activating Token Index: 440

Text #9

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1023. Min Act: -0.0001

Data Index: 1173035 (C4 (Web Text))

Max Activating Token Index: 776

Text #10

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1016. Min Act: -0.0001

Data Index: 621736 (C4 (Web Text))

Max Activating Token Index: 740

Text #11

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0995. Min Act: -0.0001

Data Index: 844960 (C4 (Web Text))

Max Activating Token Index: 791

Text #12

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1004. Min Act: -0.0001

Data Index: 1470416 (Python Code)

Max Activating Token Index: 445

Text #13

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0990. Min Act: -0.0001

Data Index: 1075077 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0990. Min Act: -0.0001

Data Index: 988937 (C4 (Web Text))

Max Activating Token Index: 453

Text #15

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0995. Min Act: -0.0001

Data Index: 630237 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0995. Min Act: -0.0001

Data Index: 1530594 (Python Code)

Max Activating Token Index: 544

Text #17

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.1000. Min Act: -0.0001

Data Index: 1178262 (C4 (Web Text))

Max Activating Token Index: 178

Text #18

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0987. Min Act: -0.0001

Data Index: 1338368 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.1142. Min Range: -0.1142

Max Act: 0.0984. Min Act: -0.0001

Data Index: 1599284 (Python Code)

Max Activating Token Index: 168