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

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

Neuron 4937 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: 0.7869. Min Range: -0.7869

Max Act: 0.7869. Min Act: -0.0000

Data Index: 924700 (C4 (Web Text))

Max Activating Token Index: 871

Text #1

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.6883. Min Act: -0.0000

Data Index: 1155985 (C4 (Web Text))

Max Activating Token Index: 1012

Text #2

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.7121. Min Act: -0.0000

Data Index: 519143 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.6298. Min Act: -0.0000

Data Index: 135503 (C4 (Web Text))

Max Activating Token Index: 337

Text #4

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.7226. Min Act: 0.0000

Data Index: 1222371 (C4 (Web Text))

Max Activating Token Index: 734

Text #5

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.6260. Min Act: -0.0000

Data Index: 451477 (C4 (Web Text))

Max Activating Token Index: 611

Text #6

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5791. Min Act: -0.0000

Data Index: 646141 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5700. Min Act: -0.0000

Data Index: 234829 (C4 (Web Text))

Max Activating Token Index: 764

Text #8

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5618. Min Act: -0.0000

Data Index: 699426 (C4 (Web Text))

Max Activating Token Index: 711

Text #9

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.6169. Min Act: -0.0000

Data Index: 62289 (C4 (Web Text))

Max Activating Token Index: 235

Text #10

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.6053. Min Act: -0.0000

Data Index: 586736 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5759. Min Act: -0.0000

Data Index: 296855 (C4 (Web Text))

Max Activating Token Index: 642

Text #12

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5671. Min Act: -0.0000

Data Index: 545374 (C4 (Web Text))

Max Activating Token Index: 523

Text #13

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.6848. Min Act: -0.0000

Data Index: 859395 (C4 (Web Text))

Max Activating Token Index: 730

Text #14

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5154. Min Act: -0.0000

Data Index: 800285 (C4 (Web Text))

Max Activating Token Index: 135

Text #15

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5185. Min Act: -0.0000

Data Index: 302006 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1166342 (C4 (Web Text))

Max Activating Token Index: 5

Text #17

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1212733 (C4 (Web Text))

Max Activating Token Index: 574

Text #18

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1099127 (C4 (Web Text))

Max Activating Token Index: 540

Text #19

Max Range: 0.7869. Min Range: -0.7869

Max Act: 0.5345. Min Act: -0.0000

Data Index: 552952 (C4 (Web Text))

Max Activating Token Index: 440