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

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

Neuron 1824 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: 3.3061. Min Range: -3.3061

Max Act: 3.1632. Min Act: -0.0000

Data Index: 883942 (C4 (Web Text))

Max Activating Token Index: 182

Text #1

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.3061. Min Act: -0.0000

Data Index: 1617178 (Python Code)

Max Activating Token Index: 704

Text #2

Max Range: 3.3061. Min Range: -3.3061

Max Act: 3.0051. Min Act: -0.0000

Data Index: 1407976 (Python Code)

Max Activating Token Index: 543

Text #3

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.8010. Min Act: -0.0000

Data Index: 1562079 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.7904. Min Act: -0.0000

Data Index: 1414266 (Python Code)

Max Activating Token Index: 278

Text #5

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.8916. Min Act: -0.0000

Data Index: 588993 (C4 (Web Text))

Max Activating Token Index: 940

Text #6

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.8107. Min Act: -0.0000

Data Index: 1470317 (Python Code)

Max Activating Token Index: 420

Text #7

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.4461. Min Act: -0.0000

Data Index: 992150 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.5581. Min Act: -0.0000

Data Index: 557785 (C4 (Web Text))

Max Activating Token Index: 589

Text #9

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.5568. Min Act: -0.0000

Data Index: 1275589 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.5372. Min Act: -0.0000

Data Index: 1085461 (C4 (Web Text))

Max Activating Token Index: 571

Text #11

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.6866. Min Act: -0.0000

Data Index: 1479740 (Python Code)

Max Activating Token Index: 1009

Text #12

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.3792. Min Act: -0.0000

Data Index: 850068 (C4 (Web Text))

Max Activating Token Index: 929

Text #13

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.6189. Min Act: -0.0000

Data Index: 979493 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.4621. Min Act: -0.0000

Data Index: 1563276 (Python Code)

Max Activating Token Index: 910

Text #15

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.4158. Min Act: -0.0000

Data Index: 1122543 (C4 (Web Text))

Max Activating Token Index: 264

Text #16

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.4053. Min Act: -0.0000

Data Index: 1649358 (Python Code)

Max Activating Token Index: 815

Text #17

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.3888. Min Act: -0.0000

Data Index: 29389 (C4 (Web Text))

Max Activating Token Index: 860

Text #18

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.2467. Min Act: -0.0000

Data Index: 1200392 (C4 (Web Text))

Max Activating Token Index: 707

Text #19

Max Range: 3.3061. Min Range: -3.3061

Max Act: 2.2067. Min Act: -0.0000

Data Index: 1488541 (Python Code)

Max Activating Token Index: 281