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

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

Neuron 2478 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.7979. Min Range: -2.7979

Max Act: 2.7979. Min Act: -0.0000

Data Index: 1116501 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 2.7979. Min Range: -2.7979

Max Act: 2.3814. Min Act: -0.0000

Data Index: 521453 (C4 (Web Text))

Max Activating Token Index: 595

Text #2

Max Range: 2.7979. Min Range: -2.7979

Max Act: 2.5368. Min Act: -0.0000

Data Index: 334800 (C4 (Web Text))

Max Activating Token Index: 879

Text #3

Max Range: 2.7979. Min Range: -2.7979

Max Act: 2.5694. Min Act: -0.0000

Data Index: 1126760 (C4 (Web Text))

Max Activating Token Index: 540

Text #4

Max Range: 2.7979. Min Range: -2.7979

Max Act: 2.2180. Min Act: -0.0000

Data Index: 557822 (C4 (Web Text))

Max Activating Token Index: 996

Text #5

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.9639. Min Act: -0.0000

Data Index: 721650 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.9917. Min Act: -0.0000

Data Index: 278394 (C4 (Web Text))

Max Activating Token Index: 230

Text #7

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.9974. Min Act: -0.0000

Data Index: 1140808 (C4 (Web Text))

Max Activating Token Index: 124

Text #8

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.7951. Min Act: -0.0000

Data Index: 407601 (C4 (Web Text))

Max Activating Token Index: 203

Text #9

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.5201. Min Act: -0.0000

Data Index: 1024586 (C4 (Web Text))

Max Activating Token Index: 42

Text #10

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.5109. Min Act: -0.0000

Data Index: 909858 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.3246. Min Act: -0.0000

Data Index: 972331 (C4 (Web Text))

Max Activating Token Index: 19

Text #12

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.3495. Min Act: -0.0000

Data Index: 804508 (C4 (Web Text))

Max Activating Token Index: 930

Text #13

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.2235. Min Act: -0.0000

Data Index: 1283504 (C4 (Web Text))

Max Activating Token Index: 762

Text #14

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.2079. Min Act: -0.0000

Data Index: 875107 (C4 (Web Text))

Max Activating Token Index: 158

Text #15

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.1370. Min Act: -0.0000

Data Index: 340302 (C4 (Web Text))

Max Activating Token Index: 39

Text #16

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.0756. Min Act: -0.0000

Data Index: 648494 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.1331. Min Act: -0.0000

Data Index: 316287 (C4 (Web Text))

Max Activating Token Index: 868

Text #18

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.1134. Min Act: -0.0000

Data Index: 576443 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 2.7979. Min Range: -2.7979

Max Act: 1.0978. Min Act: -0.0000

Data Index: 555334 (C4 (Web Text))

Max Activating Token Index: 76