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

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

Neuron 4051 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: 0.1194. Min Range: -0.1194

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1327773 (C4 (Web Text))

Max Activating Token Index: 51

Text #1

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1020. Min Act: -0.0002

Data Index: 226006 (C4 (Web Text))

Max Activating Token Index: 759

Text #2

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1110. Min Act: -0.0002

Data Index: 1519196 (Python Code)

Max Activating Token Index: 115

Text #3

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1048. Min Act: -0.0002

Data Index: 366079 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1120. Min Act: -0.0002

Data Index: 1436434 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1135. Min Act: -0.0002

Data Index: 605655 (C4 (Web Text))

Max Activating Token Index: 591

Text #6

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1163. Min Act: -0.0002

Data Index: 106625 (C4 (Web Text))

Max Activating Token Index: 651

Text #7

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1007. Min Act: -0.0002

Data Index: 744035 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1156. Min Act: -0.0002

Data Index: 891782 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1067. Min Act: -0.0002

Data Index: 306567 (C4 (Web Text))

Max Activating Token Index: 8

Text #10

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1054. Min Act: -0.0002

Data Index: 1477939 (Python Code)

Max Activating Token Index: 827

Text #11

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1032. Min Act: -0.0002

Data Index: 26961 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1018. Min Act: -0.0002

Data Index: 510060 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1044. Min Act: -0.0003

Data Index: 555488 (C4 (Web Text))

Max Activating Token Index: 608

Text #14

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1044. Min Act: -0.0002

Data Index: 1444070 (Python Code)

Max Activating Token Index: 888

Text #15

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0974. Min Act: -0.0002

Data Index: 762962 (C4 (Web Text))

Max Activating Token Index: 871

Text #16

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1194. Min Act: -0.0002

Data Index: 313004 (C4 (Web Text))

Max Activating Token Index: 705

Text #17

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0955. Min Act: -0.0002

Data Index: 1244665 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.1003. Min Act: -0.0002

Data Index: 1119248 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.1194. Min Range: -0.1194

Max Act: 0.0999. Min Act: -0.0002

Data Index: 1501765 (Python Code)

Max Activating Token Index: 316