Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3353 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.9829. Min Act: -0.0000

Data Index: 1292102 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.9915. Min Act: -0.0000

Data Index: 202817 (C4 (Web Text))

Max Activating Token Index: 835

Text #2

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1318928 (C4 (Web Text))

Max Activating Token Index: 274

Text #3

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.9143. Min Act: -0.0000

Data Index: 442255 (C4 (Web Text))

Max Activating Token Index: 156

Text #4

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8729. Min Act: -0.0000

Data Index: 483074 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8744. Min Act: -0.0000

Data Index: 846098 (C4 (Web Text))

Max Activating Token Index: 172

Text #6

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8807. Min Act: -0.0000

Data Index: 938638 (C4 (Web Text))

Max Activating Token Index: 263

Text #7

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8489. Min Act: -0.0000

Data Index: 184648 (C4 (Web Text))

Max Activating Token Index: 929

Text #8

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8988. Min Act: -0.0000

Data Index: 766329 (C4 (Web Text))

Max Activating Token Index: 531

Text #9

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8336. Min Act: -0.0000

Data Index: 21166 (C4 (Web Text))

Max Activating Token Index: 582

Text #10

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8235. Min Act: -0.0000

Data Index: 591786 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8764. Min Act: -0.0000

Data Index: 492670 (C4 (Web Text))

Max Activating Token Index: 334

Text #12

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8270. Min Act: -0.0000

Data Index: 401120 (C4 (Web Text))

Max Activating Token Index: 373

Text #13

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.7789. Min Act: -0.0000

Data Index: 775669 (C4 (Web Text))

Max Activating Token Index: 711

Text #14

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8731. Min Act: -0.0000

Data Index: 336094 (C4 (Web Text))

Max Activating Token Index: 902

Text #15

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8183. Min Act: -0.0000

Data Index: 1062800 (C4 (Web Text))

Max Activating Token Index: 42

Text #16

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8141. Min Act: -0.0000

Data Index: 296779 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8698. Min Act: -0.0000

Data Index: 867153 (C4 (Web Text))

Max Activating Token Index: 289

Text #18

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8583. Min Act: -0.0000

Data Index: 1039483 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.9915. Min Range: -0.9915

Max Act: 0.8044. Min Act: -0.0000

Data Index: 324063 (C4 (Web Text))

Max Activating Token Index: 28