Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2999 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0779. Min Act: -0.0003

Data Index: 1124370 (C4 (Web Text))

Max Activating Token Index: 696

Text #1

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0835. Min Act: -0.0003

Data Index: 1197258 (C4 (Web Text))

Max Activating Token Index: 975

Text #2

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0821. Min Act: -0.0003

Data Index: 1215361 (C4 (Web Text))

Max Activating Token Index: 116

Text #3

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0767. Min Act: -0.0003

Data Index: 67403 (C4 (Web Text))

Max Activating Token Index: 275

Text #4

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0815. Min Act: -0.0003

Data Index: 903815 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0791. Min Act: -0.0003

Data Index: 340622 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0779. Min Act: -0.0003

Data Index: 718854 (C4 (Web Text))

Max Activating Token Index: 636

Text #7

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0737. Min Act: -0.0003

Data Index: 967246 (C4 (Web Text))

Max Activating Token Index: 522

Text #8

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0802. Min Act: -0.0003

Data Index: 579602 (C4 (Web Text))

Max Activating Token Index: 40

Text #9

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0756. Min Act: -0.0003

Data Index: 1360174 (Python Code)

Max Activating Token Index: 77

Text #10

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0725. Min Act: -0.0003

Data Index: 892645 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0754. Min Act: -0.0003

Data Index: 820496 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0743. Min Act: -0.0003

Data Index: 677024 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0702. Min Act: -0.0003

Data Index: 922908 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0641. Min Act: -0.0003

Data Index: 697764 (C4 (Web Text))

Max Activating Token Index: 611

Text #15

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0758. Min Act: -0.0003

Data Index: 483927 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0727. Min Act: -0.0003

Data Index: 57725 (C4 (Web Text))

Max Activating Token Index: 364

Text #17

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0718. Min Act: -0.0003

Data Index: 1047049 (C4 (Web Text))

Max Activating Token Index: 742

Text #18

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1168025 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 0.0835. Min Range: -0.0835

Max Act: 0.0717. Min Act: -0.0003

Data Index: 221804 (C4 (Web Text))

Max Activating Token Index: 422