Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2175 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.9155. Min Act: -0.0000

Data Index: 682665 (C4 (Web Text))

Max Activating Token Index: 733

Text #1

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.9200. Min Act: -0.0000

Data Index: 478602 (C4 (Web Text))

Max Activating Token Index: 611

Text #2

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7556. Min Act: -0.0000

Data Index: 385145 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.8217. Min Act: -0.0000

Data Index: 769497 (C4 (Web Text))

Max Activating Token Index: 660

Text #4

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.7200. Min Act: -0.0000

Data Index: 759837 (C4 (Web Text))

Max Activating Token Index: 216

Text #5

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6744. Min Act: -0.0000

Data Index: 260711 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6969. Min Act: -0.0000

Data Index: 1255503 (C4 (Web Text))

Max Activating Token Index: 163

Text #7

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6733. Min Act: -0.0000

Data Index: 318246 (C4 (Web Text))

Max Activating Token Index: 922

Text #8

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6961. Min Act: -0.0000

Data Index: 941285 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6587. Min Act: -0.0000

Data Index: 669169 (C4 (Web Text))

Max Activating Token Index: 872

Text #10

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6709. Min Act: -0.0000

Data Index: 374564 (C4 (Web Text))

Max Activating Token Index: 965

Text #11

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6666. Min Act: -0.0000

Data Index: 822120 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6912. Min Act: -0.0000

Data Index: 234719 (C4 (Web Text))

Max Activating Token Index: 967

Text #13

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6516. Min Act: -0.0000

Data Index: 313688 (C4 (Web Text))

Max Activating Token Index: 179

Text #14

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1224090 (C4 (Web Text))

Max Activating Token Index: 984

Text #15

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6509. Min Act: -0.0000

Data Index: 714662 (C4 (Web Text))

Max Activating Token Index: 195

Text #16

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6212. Min Act: -0.0000

Data Index: 1146500 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6220. Min Act: -0.0000

Data Index: 140854 (C4 (Web Text))

Max Activating Token Index: 43

Text #18

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.6104. Min Act: -0.0000

Data Index: 80911 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.9200. Min Range: -0.9200

Max Act: 0.5808. Min Act: -0.0000

Data Index: 498335 (C4 (Web Text))

Max Activating Token Index: 316