Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 2045 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1965. Min Act: -0.0002

Data Index: 1312545 (C4 (Web Text))

Max Activating Token Index: 747

Text #1

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1911. Min Act: -0.0002

Data Index: 871453 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1876. Min Act: -0.0002

Data Index: 1284910 (C4 (Web Text))

Max Activating Token Index: 478

Text #3

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1894. Min Act: -0.0002

Data Index: 147722 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1895. Min Act: -0.0002

Data Index: 992584 (C4 (Web Text))

Max Activating Token Index: 383

Text #5

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1956. Min Act: -0.0002

Data Index: 491090 (C4 (Web Text))

Max Activating Token Index: 168

Text #6

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1835. Min Act: -0.0002

Data Index: 713943 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1693. Min Act: -0.0002

Data Index: 1114732 (C4 (Web Text))

Max Activating Token Index: 787

Text #8

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1760. Min Act: -0.0002

Data Index: 686442 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1804. Min Act: -0.0002

Data Index: 292538 (C4 (Web Text))

Max Activating Token Index: 135

Text #10

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1747. Min Act: -0.0002

Data Index: 670485 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1668. Min Act: -0.0002

Data Index: 1179990 (C4 (Web Text))

Max Activating Token Index: 670

Text #12

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1726. Min Act: -0.0002

Data Index: 931270 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1710. Min Act: -0.0002

Data Index: 1076990 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1811. Min Act: -0.0002

Data Index: 1073513 (C4 (Web Text))

Max Activating Token Index: 487

Text #15

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1733. Min Act: -0.0002

Data Index: 1142135 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1662. Min Act: -0.0002

Data Index: 174998 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1747. Min Act: -0.0002

Data Index: 1076389 (C4 (Web Text))

Max Activating Token Index: 172

Text #18

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1608. Min Act: -0.0002

Data Index: 753904 (C4 (Web Text))

Max Activating Token Index: 634

Text #19

Max Range: 0.1965. Min Range: -0.1965

Max Act: 0.1884. Min Act: -0.0002

Data Index: 1316729 (C4 (Web Text))

Max Activating Token Index: 143