Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2809 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.9827. Min Act: -0.0001

Data Index: 1176949 (C4 (Web Text))

Max Activating Token Index: 714

Text #1

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.9033. Min Act: -0.0001

Data Index: 788712 (C4 (Web Text))

Max Activating Token Index: 745

Text #2

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8361. Min Act: -0.0001

Data Index: 946706 (C4 (Web Text))

Max Activating Token Index: 837

Text #3

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8447. Min Act: -0.0001

Data Index: 1004320 (C4 (Web Text))

Max Activating Token Index: 157

Text #4

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8074. Min Act: -0.0001

Data Index: 204595 (C4 (Web Text))

Max Activating Token Index: 490

Text #5

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.8569. Min Act: -0.0001

Data Index: 468645 (C4 (Web Text))

Max Activating Token Index: 260

Text #6

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7969. Min Act: -0.0001

Data Index: 786623 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7003. Min Act: -0.0001

Data Index: 1184871 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7614. Min Act: -0.0001

Data Index: 574630 (C4 (Web Text))

Max Activating Token Index: 554

Text #9

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7747. Min Act: -0.0001

Data Index: 479008 (C4 (Web Text))

Max Activating Token Index: 218

Text #10

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7360. Min Act: -0.0001

Data Index: 258850 (C4 (Web Text))

Max Activating Token Index: 478

Text #11

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7468. Min Act: -0.0001

Data Index: 627167 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7475. Min Act: -0.0001

Data Index: 694132 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7425. Min Act: -0.0001

Data Index: 39215 (C4 (Web Text))

Max Activating Token Index: 297

Text #14

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7637. Min Act: -0.0001

Data Index: 844204 (C4 (Web Text))

Max Activating Token Index: 461

Text #15

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7281. Min Act: -0.0001

Data Index: 444974 (C4 (Web Text))

Max Activating Token Index: 357

Text #16

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7556. Min Act: -0.0001

Data Index: 150811 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.6871. Min Act: -0.0001

Data Index: 455490 (C4 (Web Text))

Max Activating Token Index: 697

Text #18

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7021. Min Act: -0.0001

Data Index: 425368 (C4 (Web Text))

Max Activating Token Index: 99

Text #19

Max Range: 0.9827. Min Range: -0.9827

Max Act: 0.7072. Min Act: -0.0001

Data Index: 64250 (C4 (Web Text))

Max Activating Token Index: 254