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

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

Neuron 2049 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: 1.0752. Min Range: -1.0752

Max Act: 1.0752. Min Act: -0.0000

Data Index: 922622 (C4 (Web Text))

Max Activating Token Index: 996

Text #1

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8871. Min Act: 0.0000

Data Index: 1131077 (C4 (Web Text))

Max Activating Token Index: 179

Text #2

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.9343. Min Act: -0.0000

Data Index: 265892 (C4 (Web Text))

Max Activating Token Index: 469

Text #3

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.9932. Min Act: -0.0000

Data Index: 867859 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.9059. Min Act: -0.0000

Data Index: 1099907 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8790. Min Act: 0.0000

Data Index: 1066152 (C4 (Web Text))

Max Activating Token Index: 388

Text #6

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.9445. Min Act: -0.0000

Data Index: 804270 (C4 (Web Text))

Max Activating Token Index: 675

Text #7

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8686. Min Act: -0.0000

Data Index: 903708 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8776. Min Act: -0.0000

Data Index: 1003998 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8736. Min Act: -0.0000

Data Index: 375822 (C4 (Web Text))

Max Activating Token Index: 297

Text #10

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.7854. Min Act: -0.0000

Data Index: 205633 (C4 (Web Text))

Max Activating Token Index: 822

Text #11

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8646. Min Act: -0.0000

Data Index: 888874 (C4 (Web Text))

Max Activating Token Index: 888

Text #12

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8024. Min Act: 0.0000

Data Index: 574128 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8145. Min Act: 0.0000

Data Index: 639357 (C4 (Web Text))

Max Activating Token Index: 599

Text #14

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1249992 (C4 (Web Text))

Max Activating Token Index: 120

Text #15

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.8276. Min Act: 0.0000

Data Index: 869587 (C4 (Web Text))

Max Activating Token Index: 32

Text #16

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.7697. Min Act: -0.0000

Data Index: 114292 (C4 (Web Text))

Max Activating Token Index: 819

Text #17

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.7654. Min Act: 0.0001

Data Index: 1070673 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.7645. Min Act: -0.0000

Data Index: 456602 (C4 (Web Text))

Max Activating Token Index: 1010

Text #19

Max Range: 1.0752. Min Range: -1.0752

Max Act: 0.7525. Min Act: -0.0000

Data Index: 865060 (C4 (Web Text))

Max Activating Token Index: 738