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

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

Neuron 3076 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: 0.1187. Min Range: -0.1187

Max Act: 0.1187. Min Act: -0.0001

Data Index: 920523 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1164. Min Act: -0.0001

Data Index: 98886 (C4 (Web Text))

Max Activating Token Index: 52

Text #2

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1141. Min Act: -0.0001

Data Index: 87342 (C4 (Web Text))

Max Activating Token Index: 89

Text #3

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1145. Min Act: -0.0001

Data Index: 330052 (C4 (Web Text))

Max Activating Token Index: 721

Text #4

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1141. Min Act: -0.0001

Data Index: 464482 (C4 (Web Text))

Max Activating Token Index: 784

Text #5

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1160. Min Act: -0.0001

Data Index: 408903 (C4 (Web Text))

Max Activating Token Index: 629

Text #6

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1132. Min Act: -0.0001

Data Index: 277403 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1117. Min Act: -0.0001

Data Index: 1262833 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1130. Min Act: -0.0001

Data Index: 828801 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1266291 (C4 (Web Text))

Max Activating Token Index: 136

Text #10

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1113. Min Act: -0.0001

Data Index: 466709 (C4 (Web Text))

Max Activating Token Index: 690

Text #11

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1133. Min Act: -0.0001

Data Index: 450070 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1116. Min Act: -0.0001

Data Index: 886054 (C4 (Web Text))

Max Activating Token Index: 896

Text #13

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1115. Min Act: -0.0002

Data Index: 93522 (C4 (Web Text))

Max Activating Token Index: 1006

Text #14

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1099. Min Act: -0.0001

Data Index: 163446 (C4 (Web Text))

Max Activating Token Index: 774

Text #15

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1123591 (C4 (Web Text))

Max Activating Token Index: 970

Text #16

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1245477 (C4 (Web Text))

Max Activating Token Index: 82

Text #17

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1085. Min Act: -0.0001

Data Index: 1295852 (C4 (Web Text))

Max Activating Token Index: 220

Text #18

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1118. Min Act: -0.0001

Data Index: 235503 (C4 (Web Text))

Max Activating Token Index: 734

Text #19

Max Range: 0.1187. Min Range: -0.1187

Max Act: 0.1089. Min Act: -0.0001

Data Index: 49922 (C4 (Web Text))

Max Activating Token Index: 602