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

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

Neuron 4407 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: 3.4034. Min Range: -3.4034

Max Act: 3.4034. Min Act: -0.0000

Data Index: 1106283 (C4 (Web Text))

Max Activating Token Index: 700

Text #1

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.3260. Min Act: -0.0000

Data Index: 1012737 (C4 (Web Text))

Max Activating Token Index: 788

Text #2

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.3048. Min Act: -0.0000

Data Index: 646002 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.2895. Min Act: -0.0000

Data Index: 765344 (C4 (Web Text))

Max Activating Token Index: 42

Text #4

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.1975. Min Act: -0.0000

Data Index: 395722 (C4 (Web Text))

Max Activating Token Index: 35

Text #5

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.1900. Min Act: -0.0000

Data Index: 334972 (C4 (Web Text))

Max Activating Token Index: 288

Text #6

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.0490. Min Act: -0.0000

Data Index: 728585 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.1033. Min Act: -0.0000

Data Index: 94678 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.1869. Min Act: -0.0000

Data Index: 1114567 (C4 (Web Text))

Max Activating Token Index: 944

Text #9

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.9741. Min Act: -0.0000

Data Index: 1015827 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 3.4034. Min Range: -3.4034

Max Act: 2.0714. Min Act: -0.0000

Data Index: 270213 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.9197. Min Act: -0.0000

Data Index: 21397 (C4 (Web Text))

Max Activating Token Index: 664

Text #12

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.9749. Min Act: -0.0000

Data Index: 348982 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.9597. Min Act: -0.0000

Data Index: 1435298 (Python Code)

Max Activating Token Index: 528

Text #14

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.9716. Min Act: -0.0000

Data Index: 588327 (C4 (Web Text))

Max Activating Token Index: 777

Text #15

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.9591. Min Act: -0.0000

Data Index: 561656 (C4 (Web Text))

Max Activating Token Index: 851

Text #16

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.9090. Min Act: -0.0000

Data Index: 1349805 (C4 (Web Text))

Max Activating Token Index: 824

Text #17

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.7901. Min Act: -0.0000

Data Index: 208007 (C4 (Web Text))

Max Activating Token Index: 169

Text #18

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.8757. Min Act: -0.0000

Data Index: 89935 (C4 (Web Text))

Max Activating Token Index: 560

Text #19

Max Range: 3.4034. Min Range: -3.4034

Max Act: 1.7126. Min Act: -0.0000

Data Index: 1217774 (C4 (Web Text))

Max Activating Token Index: 287