Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1654 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2544. Min Act: -0.0001

Data Index: 1487539 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2222. Min Act: -0.0001

Data Index: 1175634 (C4 (Web Text))

Max Activating Token Index: 85

Text #2

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2515. Min Act: -0.0001

Data Index: 1514112 (Python Code)

Max Activating Token Index: 708

Text #3

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2143. Min Act: -0.0002

Data Index: 346626 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2186. Min Act: -0.0001

Data Index: 956203 (C4 (Web Text))

Max Activating Token Index: 189

Text #5

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1955. Min Act: -0.0001

Data Index: 824106 (C4 (Web Text))

Max Activating Token Index: 523

Text #6

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2100. Min Act: -0.0001

Data Index: 169400 (C4 (Web Text))

Max Activating Token Index: 1018

Text #7

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2038. Min Act: -0.0001

Data Index: 381568 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1883. Min Act: -0.0001

Data Index: 317732 (C4 (Web Text))

Max Activating Token Index: 884

Text #9

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1650. Min Act: -0.0001

Data Index: 1289713 (C4 (Web Text))

Max Activating Token Index: 930

Text #10

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1824. Min Act: -0.0001

Data Index: 214888 (C4 (Web Text))

Max Activating Token Index: 281

Text #11

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1791. Min Act: -0.0001

Data Index: 1380698 (Python Code)

Max Activating Token Index: 593

Text #12

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1855. Min Act: -0.0001

Data Index: 1461480 (Python Code)

Max Activating Token Index: 460

Text #13

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2059. Min Act: -0.0001

Data Index: 885484 (C4 (Web Text))

Max Activating Token Index: 632

Text #14

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1891. Min Act: -0.0002

Data Index: 1099528 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1956. Min Act: -0.0001

Data Index: 745031 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1984. Min Act: -0.0001

Data Index: 1161147 (C4 (Web Text))

Max Activating Token Index: 946

Text #17

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1919. Min Act: -0.0001

Data Index: 296206 (C4 (Web Text))

Max Activating Token Index: 802

Text #18

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.2004. Min Act: -0.0002

Data Index: 726031 (C4 (Web Text))

Max Activating Token Index: 297

Text #19

Max Range: 0.2544. Min Range: -0.2544

Max Act: 0.1781. Min Act: -0.0002

Data Index: 667025 (C4 (Web Text))

Max Activating Token Index: 906