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

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

Neuron 4731 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.9694. Min Act: -0.0000

Data Index: 516081 (C4 (Web Text))

Max Activating Token Index: 748

Text #1

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.8270. Min Act: -0.0000

Data Index: 114445 (C4 (Web Text))

Max Activating Token Index: 741

Text #2

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.6907. Min Act: -0.0000

Data Index: 389186 (C4 (Web Text))

Max Activating Token Index: 368

Text #3

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.6729. Min Act: -0.0000

Data Index: 1106058 (C4 (Web Text))

Max Activating Token Index: 950

Text #4

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.7157. Min Act: -0.0000

Data Index: 820963 (C4 (Web Text))

Max Activating Token Index: 434

Text #5

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.8231. Min Act: -0.0000

Data Index: 110828 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.7052. Min Act: -0.0000

Data Index: 460598 (C4 (Web Text))

Max Activating Token Index: 914

Text #7

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.6928. Min Act: -0.0000

Data Index: 413177 (C4 (Web Text))

Max Activating Token Index: 428

Text #8

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.7282. Min Act: -0.0000

Data Index: 1099038 (C4 (Web Text))

Max Activating Token Index: 879

Text #9

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.6259. Min Act: -0.0000

Data Index: 11124 (C4 (Web Text))

Max Activating Token Index: 73

Text #10

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.6176. Min Act: -0.0000

Data Index: 1258135 (C4 (Web Text))

Max Activating Token Index: 902

Text #11

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.6892. Min Act: -0.0000

Data Index: 1042652 (C4 (Web Text))

Max Activating Token Index: 744

Text #12

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.4758. Min Act: -0.0000

Data Index: 1649005 (Python Code)

Max Activating Token Index: 29

Text #13

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.3087. Min Act: -0.0000

Data Index: 1310209 (C4 (Web Text))

Max Activating Token Index: 1011

Text #14

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.0053. Min Act: -0.0000

Data Index: 612780 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.0070. Min Act: -0.0000

Data Index: 792736 (C4 (Web Text))

Max Activating Token Index: 629

Text #16

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1474225 (Python Code)

Max Activating Token Index: 51

Text #17

Max Range: 1.9694. Min Range: -1.9694

Max Act: 0.9940. Min Act: -0.0000

Data Index: 434192 (C4 (Web Text))

Max Activating Token Index: 363

Text #18

Max Range: 1.9694. Min Range: -1.9694

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1320993 (C4 (Web Text))

Max Activating Token Index: 660

Text #19

Max Range: 1.9694. Min Range: -1.9694

Max Act: 0.9866. Min Act: -0.0000

Data Index: 1597874 (Python Code)

Max Activating Token Index: 45