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

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

Neuron 3753 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: 0.1125. Min Range: -0.1125

Max Act: 0.1125. Min Act: -0.0001

Data Index: 414714 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1090. Min Act: -0.0002

Data Index: 196809 (C4 (Web Text))

Max Activating Token Index: 274

Text #2

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1063. Min Act: -0.0001

Data Index: 820733 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1064. Min Act: -0.0001

Data Index: 593837 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1076. Min Act: -0.0001

Data Index: 1164320 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1048. Min Act: -0.0001

Data Index: 182572 (C4 (Web Text))

Max Activating Token Index: 283

Text #6

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1026. Min Act: -0.0001

Data Index: 462331 (C4 (Web Text))

Max Activating Token Index: 39

Text #7

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0993. Min Act: -0.0001

Data Index: 1055390 (C4 (Web Text))

Max Activating Token Index: 452

Text #8

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0995. Min Act: -0.0001

Data Index: 152453 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.1010. Min Act: -0.0001

Data Index: 278202 (C4 (Web Text))

Max Activating Token Index: 215

Text #10

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0998. Min Act: -0.0001

Data Index: 795423 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0977. Min Act: -0.0001

Data Index: 57220 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0968. Min Act: -0.0001

Data Index: 895228 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0978. Min Act: -0.0001

Data Index: 694969 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0966. Min Act: -0.0001

Data Index: 1133037 (C4 (Web Text))

Max Activating Token Index: 100

Text #15

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1151057 (C4 (Web Text))

Max Activating Token Index: 58

Text #16

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0992. Min Act: -0.0001

Data Index: 1277824 (C4 (Web Text))

Max Activating Token Index: 9

Text #17

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0968. Min Act: -0.0001

Data Index: 1048681 (C4 (Web Text))

Max Activating Token Index: 19

Text #18

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0979. Min Act: -0.0001

Data Index: 926255 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.1125. Min Range: -0.1125

Max Act: 0.0965. Min Act: -0.0001

Data Index: 982052 (C4 (Web Text))

Max Activating Token Index: 16