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

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

Neuron 2059 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.6832. Min Act: -0.0001

Data Index: 1242653 (C4 (Web Text))

Max Activating Token Index: 831

Text #1

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.5813. Min Act: -0.0001

Data Index: 963382 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.6606. Min Act: -0.0001

Data Index: 133822 (C4 (Web Text))

Max Activating Token Index: 857

Text #3

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.4581. Min Act: -0.0001

Data Index: 887396 (C4 (Web Text))

Max Activating Token Index: 51

Text #4

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.4134. Min Act: -0.0001

Data Index: 302538 (C4 (Web Text))

Max Activating Token Index: 327

Text #5

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.3145. Min Act: -0.0001

Data Index: 1454015 (Python Code)

Max Activating Token Index: 19

Text #6

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.3125. Min Act: -0.0001

Data Index: 1167551 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.3409. Min Act: -0.0001

Data Index: 36243 (C4 (Web Text))

Max Activating Token Index: 29

Text #8

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.3737. Min Act: -0.0001

Data Index: 127747 (C4 (Web Text))

Max Activating Token Index: 618

Text #9

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2394. Min Act: -0.0001

Data Index: 246298 (C4 (Web Text))

Max Activating Token Index: 324

Text #10

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.3119. Min Act: -0.0001

Data Index: 628629 (C4 (Web Text))

Max Activating Token Index: 381

Text #11

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.0741. Min Act: -0.0001

Data Index: 285446 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2008. Min Act: -0.0001

Data Index: 994400 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.2795. Min Act: -0.0001

Data Index: 66549 (C4 (Web Text))

Max Activating Token Index: 717

Text #14

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1769. Min Act: -0.0001

Data Index: 1122391 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1766. Min Act: -0.0001

Data Index: 506173 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1846. Min Act: -0.0001

Data Index: 345552 (C4 (Web Text))

Max Activating Token Index: 623

Text #17

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1742. Min Act: -0.0001

Data Index: 304755 (C4 (Web Text))

Max Activating Token Index: 649

Text #18

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.0923. Min Act: -0.0001

Data Index: 266482 (C4 (Web Text))

Max Activating Token Index: 116

Text #19

Max Range: 1.6832. Min Range: -1.6832

Max Act: 1.1166. Min Act: -0.0001

Data Index: 1551822 (Python Code)

Max Activating Token Index: 802