Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1705 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1186. Min Act: -0.0001

Data Index: 1409273 (Python Code)

Max Activating Token Index: 114

Text #1

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1182. Min Act: -0.0001

Data Index: 1382868 (Python Code)

Max Activating Token Index: 463

Text #2

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1159. Min Act: -0.0001

Data Index: 1438273 (Python Code)

Max Activating Token Index: 587

Text #3

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1425316 (Python Code)

Max Activating Token Index: 67

Text #4

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1138. Min Act: -0.0001

Data Index: 1619689 (Python Code)

Max Activating Token Index: 430

Text #5

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1130. Min Act: -0.0001

Data Index: 1434820 (Python Code)

Max Activating Token Index: 844

Text #6

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1401273 (Python Code)

Max Activating Token Index: 106

Text #7

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1437474 (Python Code)

Max Activating Token Index: 201

Text #8

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1056. Min Act: -0.0001

Data Index: 1574370 (Python Code)

Max Activating Token Index: 710

Text #9

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1026. Min Act: -0.0001

Data Index: 1456645 (Python Code)

Max Activating Token Index: 40

Text #10

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1444041 (Python Code)

Max Activating Token Index: 158

Text #11

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1010. Min Act: -0.0001

Data Index: 1607992 (Python Code)

Max Activating Token Index: 894

Text #12

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1001. Min Act: -0.0001

Data Index: 1484639 (Python Code)

Max Activating Token Index: 124

Text #13

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0982. Min Act: -0.0001

Data Index: 1463925 (Python Code)

Max Activating Token Index: 129

Text #14

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0980. Min Act: -0.0002

Data Index: 1441602 (Python Code)

Max Activating Token Index: 27

Text #15

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0979. Min Act: -0.0001

Data Index: 1407674 (Python Code)

Max Activating Token Index: 33

Text #16

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1518174 (Python Code)

Max Activating Token Index: 77

Text #17

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0972. Min Act: -0.0001

Data Index: 1531341 (Python Code)

Max Activating Token Index: 84

Text #18

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.0972. Min Act: -0.0002

Data Index: 1368322 (Python Code)

Max Activating Token Index: 161

Text #19

Max Range: 0.1186. Min Range: -0.1186

Max Act: 0.1009. Min Act: -0.0002

Data Index: 1510719 (Python Code)

Max Activating Token Index: 121