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

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

Neuron 1885 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.2264. Min Range: -4.2264

Max Act: 4.2264. Min Act: -0.0000

Data Index: 1012879 (C4 (Web Text))

Max Activating Token Index: 681

Text #1

Max Range: 4.2264. Min Range: -4.2264

Max Act: 3.7789. Min Act: -0.0000

Data Index: 187051 (C4 (Web Text))

Max Activating Token Index: 264

Text #2

Max Range: 4.2264. Min Range: -4.2264

Max Act: 4.0350. Min Act: -0.0000

Data Index: 1213078 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 4.2264. Min Range: -4.2264

Max Act: 3.8704. Min Act: -0.0000

Data Index: 27843 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 4.2264. Min Range: -4.2264

Max Act: 3.6396. Min Act: -0.0000

Data Index: 245912 (C4 (Web Text))

Max Activating Token Index: 277

Text #5

Max Range: 4.2264. Min Range: -4.2264

Max Act: 3.1840. Min Act: -0.0000

Data Index: 1466863 (Python Code)

Max Activating Token Index: 908

Text #6

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.8620. Min Act: -0.0000

Data Index: 562890 (C4 (Web Text))

Max Activating Token Index: 75

Text #7

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.9287. Min Act: -0.0000

Data Index: 1037440 (C4 (Web Text))

Max Activating Token Index: 389

Text #8

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.7293. Min Act: -0.0000

Data Index: 592399 (C4 (Web Text))

Max Activating Token Index: 934

Text #9

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.8183. Min Act: -0.0000

Data Index: 458670 (C4 (Web Text))

Max Activating Token Index: 960

Text #10

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.7636. Min Act: -0.0000

Data Index: 1329092 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.6940. Min Act: -0.0000

Data Index: 927825 (C4 (Web Text))

Max Activating Token Index: 173

Text #12

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.5912. Min Act: -0.0000

Data Index: 1170275 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.5908. Min Act: -0.0000

Data Index: 378775 (C4 (Web Text))

Max Activating Token Index: 964

Text #14

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.6438. Min Act: -0.0000

Data Index: 1267904 (C4 (Web Text))

Max Activating Token Index: 538

Text #15

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.6158. Min Act: -0.0000

Data Index: 68067 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.5940. Min Act: -0.0000

Data Index: 869420 (C4 (Web Text))

Max Activating Token Index: 661

Text #17

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.5857. Min Act: -0.0000

Data Index: 277902 (C4 (Web Text))

Max Activating Token Index: 12

Text #18

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.7016. Min Act: -0.0000

Data Index: 29686 (C4 (Web Text))

Max Activating Token Index: 517

Text #19

Max Range: 4.2264. Min Range: -4.2264

Max Act: 2.5563. Min Act: -0.0000

Data Index: 1541384 (Python Code)

Max Activating Token Index: 1023