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

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

Neuron 753 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2535. Min Act: -0.0000

Data Index: 796989 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2505. Min Act: -0.0000

Data Index: 1133980 (C4 (Web Text))

Max Activating Token Index: 776

Text #2

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2254. Min Act: -0.0000

Data Index: 862939 (C4 (Web Text))

Max Activating Token Index: 258

Text #3

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2065. Min Act: -0.0000

Data Index: 1121880 (C4 (Web Text))

Max Activating Token Index: 982

Text #4

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2193. Min Act: -0.0000

Data Index: 394299 (C4 (Web Text))

Max Activating Token Index: 951

Text #5

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1938. Min Act: -0.0000

Data Index: 173784 (C4 (Web Text))

Max Activating Token Index: 175

Text #6

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1967. Min Act: -0.0000

Data Index: 593988 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1895. Min Act: -0.0000

Data Index: 1262530 (C4 (Web Text))

Max Activating Token Index: 159

Text #8

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.2007. Min Act: -0.0000

Data Index: 290513 (C4 (Web Text))

Max Activating Token Index: 564

Text #9

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1778. Min Act: -0.0000

Data Index: 766662 (C4 (Web Text))

Max Activating Token Index: 260

Text #10

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1948. Min Act: -0.0000

Data Index: 34985 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1862. Min Act: -0.0000

Data Index: 23719 (C4 (Web Text))

Max Activating Token Index: 427

Text #12

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1879. Min Act: -0.0000

Data Index: 828753 (C4 (Web Text))

Max Activating Token Index: 1002

Text #13

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1852. Min Act: -0.0000

Data Index: 969969 (C4 (Web Text))

Max Activating Token Index: 238

Text #14

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1796. Min Act: -0.0000

Data Index: 1199695 (C4 (Web Text))

Max Activating Token Index: 296

Text #15

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1800. Min Act: -0.0000

Data Index: 1206675 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1752. Min Act: -0.0000

Data Index: 1148314 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1737. Min Act: -0.0000

Data Index: 179025 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1794. Min Act: -0.0000

Data Index: 386220 (C4 (Web Text))

Max Activating Token Index: 579

Text #19

Max Range: 0.2535. Min Range: -0.2535

Max Act: 0.1785. Min Act: -0.0000

Data Index: 372878 (C4 (Web Text))

Max Activating Token Index: 590