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

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

Neuron 2958 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1353. Min Act: -0.0002

Data Index: 428819 (C4 (Web Text))

Max Activating Token Index: 9

Text #1

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1259. Min Act: -0.0002

Data Index: 745818 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1104. Min Act: -0.0002

Data Index: 450536 (C4 (Web Text))

Max Activating Token Index: 66

Text #3

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1153. Min Act: -0.0002

Data Index: 385384 (C4 (Web Text))

Max Activating Token Index: 4

Text #4

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1331. Min Act: -0.0002

Data Index: 1349987 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1145. Min Act: -0.0002

Data Index: 413811 (C4 (Web Text))

Max Activating Token Index: 16

Text #6

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1153. Min Act: -0.0002

Data Index: 111764 (C4 (Web Text))

Max Activating Token Index: 17

Text #7

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1093. Min Act: -0.0002

Data Index: 1315027 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0992. Min Act: -0.0002

Data Index: 902213 (C4 (Web Text))

Max Activating Token Index: 258

Text #9

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1086. Min Act: -0.0002

Data Index: 752901 (C4 (Web Text))

Max Activating Token Index: 21

Text #10

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1075. Min Act: -0.0002

Data Index: 616255 (C4 (Web Text))

Max Activating Token Index: 35

Text #11

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1080. Min Act: -0.0002

Data Index: 1296589 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1281428 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1090. Min Act: -0.0002

Data Index: 376952 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1039. Min Act: -0.0002

Data Index: 393613 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1036. Min Act: -0.0002

Data Index: 518950 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1021. Min Act: -0.0002

Data Index: 748668 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1020. Min Act: -0.0002

Data Index: 59785 (C4 (Web Text))

Max Activating Token Index: 302

Text #18

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.1023. Min Act: -0.0002

Data Index: 941907 (C4 (Web Text))

Max Activating Token Index: 11

Text #19

Max Range: 0.1353. Min Range: -0.1353

Max Act: 0.0994. Min Act: -0.0002

Data Index: 709156 (C4 (Web Text))

Max Activating Token Index: 882