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

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

Neuron 1223 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2585. Min Act: -0.0000

Data Index: 1350420 (C4 (Web Text))

Max Activating Token Index: 518

Text #1

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2298. Min Act: -0.0000

Data Index: 967969 (C4 (Web Text))

Max Activating Token Index: 38

Text #2

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2148. Min Act: -0.0001

Data Index: 1153903 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2267. Min Act: -0.0000

Data Index: 693468 (C4 (Web Text))

Max Activating Token Index: 508

Text #4

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2103. Min Act: -0.0001

Data Index: 96809 (C4 (Web Text))

Max Activating Token Index: 111

Text #5

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2047. Min Act: -0.0000

Data Index: 1184180 (C4 (Web Text))

Max Activating Token Index: 674

Text #6

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.2005. Min Act: -0.0000

Data Index: 1163466 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1949. Min Act: -0.0000

Data Index: 680215 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1987. Min Act: -0.0001

Data Index: 1211342 (C4 (Web Text))

Max Activating Token Index: 891

Text #9

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1259729 (C4 (Web Text))

Max Activating Token Index: 938

Text #10

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1844. Min Act: -0.0001

Data Index: 688043 (C4 (Web Text))

Max Activating Token Index: 562

Text #11

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1817. Min Act: -0.0000

Data Index: 733539 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1748. Min Act: -0.0000

Data Index: 488832 (C4 (Web Text))

Max Activating Token Index: 990

Text #13

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1894. Min Act: -0.0000

Data Index: 478022 (C4 (Web Text))

Max Activating Token Index: 647

Text #14

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1798. Min Act: -0.0000

Data Index: 252771 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1706. Min Act: 0.0000

Data Index: 927299 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1770. Min Act: 0.0000

Data Index: 271201 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1789. Min Act: -0.0000

Data Index: 641330 (C4 (Web Text))

Max Activating Token Index: 911

Text #18

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1728. Min Act: -0.0000

Data Index: 644625 (C4 (Web Text))

Max Activating Token Index: 857

Text #19

Max Range: 0.2585. Min Range: -0.2585

Max Act: 0.1727. Min Act: -0.0000

Data Index: 639934 (C4 (Web Text))

Max Activating Token Index: 475