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

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

Neuron 2944 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1537. Min Act: -0.0002

Data Index: 1303196 (C4 (Web Text))

Max Activating Token Index: 15

Text #1

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1425. Min Act: -0.0002

Data Index: 715928 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1364. Min Act: -0.0002

Data Index: 831459 (C4 (Web Text))

Max Activating Token Index: 35

Text #3

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1309. Min Act: -0.0002

Data Index: 1055934 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1224. Min Act: -0.0002

Data Index: 1257764 (C4 (Web Text))

Max Activating Token Index: 406

Text #5

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1217. Min Act: -0.0002

Data Index: 101870 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1268. Min Act: -0.0002

Data Index: 766185 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1157. Min Act: -0.0002

Data Index: 85653 (C4 (Web Text))

Max Activating Token Index: 567

Text #8

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1130. Min Act: -0.0002

Data Index: 855392 (C4 (Web Text))

Max Activating Token Index: 396

Text #9

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1155. Min Act: -0.0002

Data Index: 802746 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1131. Min Act: -0.0002

Data Index: 303201 (C4 (Web Text))

Max Activating Token Index: 986

Text #11

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1074. Min Act: -0.0002

Data Index: 188032 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1014. Min Act: -0.0002

Data Index: 1441862 (Python Code)

Max Activating Token Index: 266

Text #13

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1071. Min Act: -0.0003

Data Index: 539163 (C4 (Web Text))

Max Activating Token Index: 897

Text #14

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1038. Min Act: -0.0002

Data Index: 1104323 (C4 (Web Text))

Max Activating Token Index: 299

Text #15

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1071. Min Act: -0.0002

Data Index: 353643 (C4 (Web Text))

Max Activating Token Index: 482

Text #16

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1068. Min Act: -0.0002

Data Index: 496797 (C4 (Web Text))

Max Activating Token Index: 751

Text #17

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.0987. Min Act: -0.0002

Data Index: 1466759 (Python Code)

Max Activating Token Index: 173

Text #18

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1024. Min Act: -0.0002

Data Index: 1419098 (Python Code)

Max Activating Token Index: 117

Text #19

Max Range: 0.1537. Min Range: -0.1537

Max Act: 0.1019. Min Act: -0.0003

Data Index: 1067451 (C4 (Web Text))

Max Activating Token Index: 1009