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

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

Neuron 4995 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: 0.5097. Min Range: -0.5097

Max Act: 0.5097. Min Act: -0.0000

Data Index: 583393 (C4 (Web Text))

Max Activating Token Index: 420

Text #1

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4741. Min Act: 0.0000

Data Index: 687100 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.5008. Min Act: -0.0000

Data Index: 815257 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4995. Min Act: 0.0000

Data Index: 1188423 (C4 (Web Text))

Max Activating Token Index: 881

Text #4

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4658. Min Act: -0.0000

Data Index: 722599 (C4 (Web Text))

Max Activating Token Index: 619

Text #5

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4538. Min Act: -0.0000

Data Index: 483043 (C4 (Web Text))

Max Activating Token Index: 1002

Text #6

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4395. Min Act: -0.0000

Data Index: 1222889 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4437. Min Act: -0.0000

Data Index: 455652 (C4 (Web Text))

Max Activating Token Index: 619

Text #8

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4206. Min Act: -0.0000

Data Index: 1149958 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4036. Min Act: 0.0000

Data Index: 987746 (C4 (Web Text))

Max Activating Token Index: 481

Text #10

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4114. Min Act: -0.0000

Data Index: 471013 (C4 (Web Text))

Max Activating Token Index: 334

Text #11

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4115. Min Act: 0.0001

Data Index: 929760 (C4 (Web Text))

Max Activating Token Index: 870

Text #12

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3993. Min Act: -0.0000

Data Index: 615119 (C4 (Web Text))

Max Activating Token Index: 446

Text #13

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3845. Min Act: -0.0000

Data Index: 160638 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3836. Min Act: -0.0000

Data Index: 31186 (C4 (Web Text))

Max Activating Token Index: 31

Text #15

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3939. Min Act: 0.0000

Data Index: 276842 (C4 (Web Text))

Max Activating Token Index: 182

Text #16

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.4166. Min Act: -0.0000

Data Index: 841005 (C4 (Web Text))

Max Activating Token Index: 320

Text #17

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3730. Min Act: 0.0000

Data Index: 980319 (C4 (Web Text))

Max Activating Token Index: 956

Text #18

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3955. Min Act: -0.0000

Data Index: 338136 (C4 (Web Text))

Max Activating Token Index: 805

Text #19

Max Range: 0.5097. Min Range: -0.5097

Max Act: 0.3842. Min Act: -0.0000

Data Index: 569943 (C4 (Web Text))

Max Activating Token Index: 97