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

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

Neuron 3992 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0072. Min Range: -1.0072

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1027958 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.0072. Min Range: -1.0072

Max Act: 1.0072. Min Act: -0.0000

Data Index: 1307560 (C4 (Web Text))

Max Activating Token Index: 778

Text #2

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.9338. Min Act: -0.0000

Data Index: 49968 (C4 (Web Text))

Max Activating Token Index: 19

Text #3

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8901. Min Act: -0.0000

Data Index: 885292 (C4 (Web Text))

Max Activating Token Index: 187

Text #4

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8797. Min Act: -0.0000

Data Index: 1015115 (C4 (Web Text))

Max Activating Token Index: 559

Text #5

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8114. Min Act: -0.0000

Data Index: 1156622 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8098. Min Act: -0.0000

Data Index: 285645 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8310. Min Act: -0.0000

Data Index: 101821 (C4 (Web Text))

Max Activating Token Index: 252

Text #8

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8851. Min Act: -0.0000

Data Index: 434280 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8870. Min Act: -0.0000

Data Index: 154746 (C4 (Web Text))

Max Activating Token Index: 953

Text #10

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8276. Min Act: -0.0000

Data Index: 1265131 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8356. Min Act: -0.0000

Data Index: 569578 (C4 (Web Text))

Max Activating Token Index: 243

Text #12

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8435. Min Act: -0.0000

Data Index: 32357 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8701. Min Act: -0.0000

Data Index: 189113 (C4 (Web Text))

Max Activating Token Index: 618

Text #14

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1065115 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8071. Min Act: -0.0000

Data Index: 187869 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7739. Min Act: -0.0000

Data Index: 399097 (C4 (Web Text))

Max Activating Token Index: 414

Text #17

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.7690. Min Act: -0.0000

Data Index: 975018 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8395. Min Act: -0.0000

Data Index: 42669 (C4 (Web Text))

Max Activating Token Index: 595

Text #19

Max Range: 1.0072. Min Range: -1.0072

Max Act: 0.8532. Min Act: -0.0000

Data Index: 358745 (C4 (Web Text))

Max Activating Token Index: 211