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

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

Neuron 3300 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: 0.7871. Min Range: -0.7871

Max Act: 0.7871. Min Act: -0.0000

Data Index: 460570 (C4 (Web Text))

Max Activating Token Index: 669

Text #1

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.7641. Min Act: -0.0000

Data Index: 557676 (C4 (Web Text))

Max Activating Token Index: 61

Text #2

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6695. Min Act: -0.0000

Data Index: 201615 (C4 (Web Text))

Max Activating Token Index: 302

Text #3

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6931. Min Act: -0.0000

Data Index: 317105 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6812. Min Act: -0.0000

Data Index: 847433 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6819. Min Act: -0.0000

Data Index: 508817 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6559. Min Act: -0.0000

Data Index: 71060 (C4 (Web Text))

Max Activating Token Index: 49

Text #7

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6325. Min Act: -0.0000

Data Index: 334983 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6369. Min Act: -0.0000

Data Index: 475421 (C4 (Web Text))

Max Activating Token Index: 14

Text #9

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6164. Min Act: -0.0000

Data Index: 699928 (C4 (Web Text))

Max Activating Token Index: 996

Text #10

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6671. Min Act: -0.0000

Data Index: 164345 (C4 (Web Text))

Max Activating Token Index: 219

Text #11

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6272. Min Act: -0.0000

Data Index: 724209 (C4 (Web Text))

Max Activating Token Index: 989

Text #12

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6285. Min Act: -0.0000

Data Index: 808361 (C4 (Web Text))

Max Activating Token Index: 1017

Text #13

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6409. Min Act: -0.0000

Data Index: 999232 (C4 (Web Text))

Max Activating Token Index: 151

Text #14

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.6213. Min Act: -0.0000

Data Index: 600093 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5886. Min Act: -0.0000

Data Index: 899344 (C4 (Web Text))

Max Activating Token Index: 596

Text #16

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5903. Min Act: -0.0000

Data Index: 360107 (C4 (Web Text))

Max Activating Token Index: 294

Text #17

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1325312 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5676. Min Act: -0.0000

Data Index: 86886 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 0.7871. Min Range: -0.7871

Max Act: 0.5836. Min Act: -0.0000

Data Index: 57970 (C4 (Web Text))

Max Activating Token Index: 192