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

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

Neuron 4190 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.5914. Min Act: -0.0000

Data Index: 827569 (C4 (Web Text))

Max Activating Token Index: 920

Text #1

Max Range: 4.5914. Min Range: -4.5914

Max Act: 4.5701. Min Act: -0.0000

Data Index: 561332 (C4 (Web Text))

Max Activating Token Index: 524

Text #2

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.7444. Min Act: -0.0000

Data Index: 296190 (C4 (Web Text))

Max Activating Token Index: 217

Text #3

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.8637. Min Act: -0.0000

Data Index: 1135776 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.8062. Min Act: -0.0000

Data Index: 881224 (C4 (Web Text))

Max Activating Token Index: 530

Text #5

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.7472. Min Act: -0.0000

Data Index: 1220691 (C4 (Web Text))

Max Activating Token Index: 630

Text #6

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.3978. Min Act: -0.0000

Data Index: 887339 (C4 (Web Text))

Max Activating Token Index: 983

Text #7

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.8568. Min Act: -0.0000

Data Index: 553163 (C4 (Web Text))

Max Activating Token Index: 987

Text #8

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.2179. Min Act: -0.0000

Data Index: 382886 (C4 (Web Text))

Max Activating Token Index: 259

Text #9

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.4733. Min Act: -0.0000

Data Index: 1126846 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.4772. Min Act: -0.0000

Data Index: 328792 (C4 (Web Text))

Max Activating Token Index: 328

Text #11

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.4615. Min Act: -0.0000

Data Index: 1278110 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.5758. Min Act: -0.0000

Data Index: 1024886 (C4 (Web Text))

Max Activating Token Index: 965

Text #13

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.5110. Min Act: -0.0000

Data Index: 878353 (C4 (Web Text))

Max Activating Token Index: 59

Text #14

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.2927. Min Act: -0.0000

Data Index: 915786 (C4 (Web Text))

Max Activating Token Index: 880

Text #15

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.3894. Min Act: -0.0000

Data Index: 591147 (C4 (Web Text))

Max Activating Token Index: 668

Text #16

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.1988. Min Act: -0.0000

Data Index: 695386 (C4 (Web Text))

Max Activating Token Index: 650

Text #17

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.0506. Min Act: -0.0000

Data Index: 1113289 (C4 (Web Text))

Max Activating Token Index: 960

Text #18

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.1666. Min Act: -0.0000

Data Index: 820530 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 4.5914. Min Range: -4.5914

Max Act: 3.0259. Min Act: -0.0000

Data Index: 583482 (C4 (Web Text))

Max Activating Token Index: 344