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

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

Neuron 2179 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: 0.1196. Min Range: -0.1196

Max Act: 0.1162. Min Act: -0.0001

Data Index: 624322 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1182. Min Act: -0.0001

Data Index: 827437 (C4 (Web Text))

Max Activating Token Index: 15

Text #2

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1166. Min Act: -0.0001

Data Index: 1139407 (C4 (Web Text))

Max Activating Token Index: 110

Text #3

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1196. Min Act: -0.0001

Data Index: 211297 (C4 (Web Text))

Max Activating Token Index: 63

Text #4

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1137. Min Act: -0.0001

Data Index: 1145004 (C4 (Web Text))

Max Activating Token Index: 78

Text #5

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1121. Min Act: -0.0001

Data Index: 1328486 (C4 (Web Text))

Max Activating Token Index: 127

Text #6

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1115. Min Act: -0.0001

Data Index: 464957 (C4 (Web Text))

Max Activating Token Index: 578

Text #7

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1096. Min Act: -0.0001

Data Index: 962106 (C4 (Web Text))

Max Activating Token Index: 83

Text #8

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1088. Min Act: -0.0001

Data Index: 193475 (C4 (Web Text))

Max Activating Token Index: 75

Text #9

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1093298 (C4 (Web Text))

Max Activating Token Index: 479

Text #10

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1090. Min Act: -0.0001

Data Index: 194322 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1110. Min Act: -0.0001

Data Index: 1314984 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1099. Min Act: -0.0001

Data Index: 584128 (C4 (Web Text))

Max Activating Token Index: 228

Text #13

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1084. Min Act: -0.0001

Data Index: 1001352 (C4 (Web Text))

Max Activating Token Index: 73

Text #14

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1109. Min Act: -0.0001

Data Index: 47792 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1091. Min Act: -0.0001

Data Index: 591510 (C4 (Web Text))

Max Activating Token Index: 137

Text #16

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1114. Min Act: -0.0001

Data Index: 1048946 (C4 (Web Text))

Max Activating Token Index: 256

Text #17

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1074. Min Act: -0.0001

Data Index: 919972 (C4 (Web Text))

Max Activating Token Index: 41

Text #18

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1098. Min Act: -0.0001

Data Index: 1560747 (Python Code)

Max Activating Token Index: 702

Text #19

Max Range: 0.1196. Min Range: -0.1196

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1284242 (C4 (Web Text))

Max Activating Token Index: 234