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

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

Neuron 3860 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.0752. Min Range: -4.0752

Max Act: 4.0752. Min Act: -0.0000

Data Index: 1076425 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.9791. Min Act: -0.0000

Data Index: 251880 (C4 (Web Text))

Max Activating Token Index: 1009

Text #2

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.8013. Min Act: -0.0000

Data Index: 268061 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.8431. Min Act: -0.0000

Data Index: 447968 (C4 (Web Text))

Max Activating Token Index: 876

Text #4

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.4746. Min Act: -0.0000

Data Index: 366297 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.6636. Min Act: -0.0000

Data Index: 77888 (C4 (Web Text))

Max Activating Token Index: 111

Text #6

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.4974. Min Act: -0.0000

Data Index: 1002719 (C4 (Web Text))

Max Activating Token Index: 300

Text #7

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.1234. Min Act: -0.0000

Data Index: 1356023 (C4 (Web Text))

Max Activating Token Index: 672

Text #8

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.3208. Min Act: -0.0000

Data Index: 373660 (C4 (Web Text))

Max Activating Token Index: 932

Text #9

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.5079. Min Act: -0.0000

Data Index: 1042655 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.4093. Min Act: -0.0000

Data Index: 855794 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.0917. Min Act: -0.0000

Data Index: 698585 (C4 (Web Text))

Max Activating Token Index: 740

Text #12

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.2440. Min Act: -0.0000

Data Index: 898854 (C4 (Web Text))

Max Activating Token Index: 947

Text #13

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.6150. Min Act: -0.0000

Data Index: 1598598 (Python Code)

Max Activating Token Index: 838

Text #14

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.2719. Min Act: -0.0000

Data Index: 317128 (C4 (Web Text))

Max Activating Token Index: 386

Text #15

Max Range: 4.0752. Min Range: -4.0752

Max Act: 2.9564. Min Act: -0.0000

Data Index: 1253531 (C4 (Web Text))

Max Activating Token Index: 974

Text #16

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.1736. Min Act: -0.0000

Data Index: 1074727 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.0916. Min Act: -0.0000

Data Index: 1287245 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 4.0752. Min Range: -4.0752

Max Act: 2.9402. Min Act: -0.0000

Data Index: 57573 (C4 (Web Text))

Max Activating Token Index: 51

Text #19

Max Range: 4.0752. Min Range: -4.0752

Max Act: 3.0583. Min Act: -0.0000

Data Index: 914790 (C4 (Web Text))

Max Activating Token Index: 794