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

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

Neuron 3470 in Layer 1

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: 0.1459. Min Range: -0.1459

Max Act: 0.1459. Min Act: -0.0002

Data Index: 1475264 (Python Code)

Max Activating Token Index: 208

Text #1

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1263. Min Act: -0.0002

Data Index: 1599736 (Python Code)

Max Activating Token Index: 86

Text #2

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1166. Min Act: -0.0002

Data Index: 1588198 (Python Code)

Max Activating Token Index: 782

Text #3

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1200. Min Act: -0.0002

Data Index: 201286 (C4 (Web Text))

Max Activating Token Index: 164

Text #4

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1163. Min Act: -0.0002

Data Index: 73983 (C4 (Web Text))

Max Activating Token Index: 159

Text #5

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1174. Min Act: -0.0002

Data Index: 1595941 (Python Code)

Max Activating Token Index: 127

Text #6

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1555336 (Python Code)

Max Activating Token Index: 68

Text #7

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1142. Min Act: -0.0002

Data Index: 1459936 (Python Code)

Max Activating Token Index: 177

Text #8

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1121. Min Act: -0.0002

Data Index: 1648991 (Python Code)

Max Activating Token Index: 299

Text #9

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1436481 (Python Code)

Max Activating Token Index: 114

Text #10

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1139. Min Act: -0.0002

Data Index: 1608140 (Python Code)

Max Activating Token Index: 265

Text #11

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1138. Min Act: -0.0002

Data Index: 1368853 (Python Code)

Max Activating Token Index: 269

Text #12

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1127. Min Act: -0.0002

Data Index: 1523775 (Python Code)

Max Activating Token Index: 388

Text #13

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1113. Min Act: -0.0002

Data Index: 1498148 (Python Code)

Max Activating Token Index: 163

Text #14

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1096. Min Act: -0.0002

Data Index: 804913 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1119. Min Act: -0.0002

Data Index: 1636325 (Python Code)

Max Activating Token Index: 642

Text #16

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1108. Min Act: -0.0002

Data Index: 1150105 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1587028 (Python Code)

Max Activating Token Index: 76

Text #18

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1094. Min Act: -0.0002

Data Index: 1646999 (Python Code)

Max Activating Token Index: 126

Text #19

Max Range: 0.1459. Min Range: -0.1459

Max Act: 0.1097. Min Act: -0.0002

Data Index: 1643247 (Python Code)

Max Activating Token Index: 731