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

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

Neuron 4870 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2782. Min Act: -0.0000

Data Index: 1097478 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2652. Min Act: -0.0000

Data Index: 1171347 (C4 (Web Text))

Max Activating Token Index: 150

Text #2

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2361. Min Act: -0.0000

Data Index: 1093582 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2340. Min Act: -0.0000

Data Index: 197059 (C4 (Web Text))

Max Activating Token Index: 973

Text #4

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2461. Min Act: -0.0000

Data Index: 1174846 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2119. Min Act: -0.0000

Data Index: 850364 (C4 (Web Text))

Max Activating Token Index: 692

Text #6

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2173. Min Act: -0.0000

Data Index: 384831 (C4 (Web Text))

Max Activating Token Index: 227

Text #7

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2027. Min Act: -0.0000

Data Index: 1169613 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1990. Min Act: -0.0000

Data Index: 272523 (C4 (Web Text))

Max Activating Token Index: 532

Text #9

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.2065. Min Act: -0.0000

Data Index: 786881 (C4 (Web Text))

Max Activating Token Index: 375

Text #10

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1939. Min Act: -0.0000

Data Index: 698014 (C4 (Web Text))

Max Activating Token Index: 698

Text #11

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1867. Min Act: -0.0000

Data Index: 884131 (C4 (Web Text))

Max Activating Token Index: 654

Text #12

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1901. Min Act: -0.0000

Data Index: 666932 (C4 (Web Text))

Max Activating Token Index: 858

Text #13

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1838. Min Act: -0.0000

Data Index: 648505 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1731. Min Act: -0.0000

Data Index: 1251372 (C4 (Web Text))

Max Activating Token Index: 971

Text #15

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1830. Min Act: -0.0000

Data Index: 457780 (C4 (Web Text))

Max Activating Token Index: 272

Text #16

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1690. Min Act: -0.0000

Data Index: 315664 (C4 (Web Text))

Max Activating Token Index: 923

Text #17

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1638. Min Act: -0.0000

Data Index: 167146 (C4 (Web Text))

Max Activating Token Index: 904

Text #18

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1790. Min Act: -0.0000

Data Index: 735371 (C4 (Web Text))

Max Activating Token Index: 334

Text #19

Max Range: 0.2782. Min Range: -0.2782

Max Act: 0.1522. Min Act: -0.0000

Data Index: 169724 (C4 (Web Text))

Max Activating Token Index: 267