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

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

Neuron 4751 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1275. Min Act: -0.0001

Data Index: 666233 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1108. Min Act: -0.0001

Data Index: 222897 (C4 (Web Text))

Max Activating Token Index: 918

Text #2

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0930. Min Act: -0.0001

Data Index: 782921 (C4 (Web Text))

Max Activating Token Index: 224

Text #3

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1075. Min Act: -0.0000

Data Index: 1125226 (C4 (Web Text))

Max Activating Token Index: 240

Text #4

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1021. Min Act: -0.0001

Data Index: 124803 (C4 (Web Text))

Max Activating Token Index: 860

Text #5

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1011. Min Act: -0.0000

Data Index: 1340250 (C4 (Web Text))

Max Activating Token Index: 668

Text #6

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0936. Min Act: -0.0001

Data Index: 1204180 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0926. Min Act: -0.0001

Data Index: 851213 (C4 (Web Text))

Max Activating Token Index: 950

Text #8

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0961. Min Act: -0.0001

Data Index: 443125 (C4 (Web Text))

Max Activating Token Index: 149

Text #9

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.1008. Min Act: -0.0000

Data Index: 653549 (C4 (Web Text))

Max Activating Token Index: 687

Text #10

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0986. Min Act: -0.0000

Data Index: 207785 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0893. Min Act: -0.0000

Data Index: 428869 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0984. Min Act: -0.0001

Data Index: 892674 (C4 (Web Text))

Max Activating Token Index: 101

Text #13

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0945. Min Act: -0.0000

Data Index: 609455 (C4 (Web Text))

Max Activating Token Index: 33

Text #14

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0979. Min Act: -0.0000

Data Index: 1315422 (C4 (Web Text))

Max Activating Token Index: 882

Text #15

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0955. Min Act: -0.0001

Data Index: 1186463 (C4 (Web Text))

Max Activating Token Index: 599

Text #16

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0911. Min Act: -0.0001

Data Index: 702092 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0965. Min Act: -0.0001

Data Index: 1252614 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0953. Min Act: -0.0001

Data Index: 475575 (C4 (Web Text))

Max Activating Token Index: 481

Text #19

Max Range: 0.1275. Min Range: -0.1275

Max Act: 0.0907. Min Act: -0.0001

Data Index: 673707 (C4 (Web Text))

Max Activating Token Index: 532