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

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

Neuron 325 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1207. Min Act: -0.0000

Data Index: 116869 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1258. Min Act: -0.0000

Data Index: 637925 (C4 (Web Text))

Max Activating Token Index: 996

Text #2

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1173297 (C4 (Web Text))

Max Activating Token Index: 969

Text #3

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1086. Min Act: -0.0000

Data Index: 929546 (C4 (Web Text))

Max Activating Token Index: 270

Text #4

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1139. Min Act: -0.0000

Data Index: 1356241 (C4 (Web Text))

Max Activating Token Index: 753

Text #5

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1048. Min Act: -0.0000

Data Index: 251339 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1002. Min Act: -0.0000

Data Index: 177193 (C4 (Web Text))

Max Activating Token Index: 858

Text #7

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1036. Min Act: -0.0000

Data Index: 819173 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1005. Min Act: -0.0000

Data Index: 88130 (C4 (Web Text))

Max Activating Token Index: 378

Text #9

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0969. Min Act: -0.0000

Data Index: 1029258 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1006. Min Act: -0.0000

Data Index: 1261633 (C4 (Web Text))

Max Activating Token Index: 485

Text #11

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1018. Min Act: -0.0000

Data Index: 1106646 (C4 (Web Text))

Max Activating Token Index: 1018

Text #12

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.1056. Min Act: -0.0000

Data Index: 1044724 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0933. Min Act: -0.0000

Data Index: 405742 (C4 (Web Text))

Max Activating Token Index: 800

Text #14

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0961. Min Act: -0.0000

Data Index: 618343 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0890. Min Act: -0.0000

Data Index: 763105 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0915. Min Act: -0.0000

Data Index: 393978 (C4 (Web Text))

Max Activating Token Index: 187

Text #17

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0973. Min Act: -0.0000

Data Index: 847963 (C4 (Web Text))

Max Activating Token Index: 971

Text #18

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0936. Min Act: -0.0000

Data Index: 866390 (C4 (Web Text))

Max Activating Token Index: 782

Text #19

Max Range: 0.1258. Min Range: -0.1258

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1130253 (C4 (Web Text))

Max Activating Token Index: 1005