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

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

Neuron 907 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: 2.4632. Min Range: -2.4632

Max Act: 2.4632. Min Act: -0.0000

Data Index: 1452237 (Python Code)

Max Activating Token Index: 92

Text #1

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.0492. Min Act: -0.0000

Data Index: 1371847 (Python Code)

Max Activating Token Index: 690

Text #2

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.0258. Min Act: -0.0000

Data Index: 450756 (C4 (Web Text))

Max Activating Token Index: 686

Text #3

Max Range: 2.4632. Min Range: -2.4632

Max Act: 2.0037. Min Act: -0.0000

Data Index: 1489994 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.9467. Min Act: -0.0000

Data Index: 1570337 (Python Code)

Max Activating Token Index: 581

Text #5

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.8623. Min Act: -0.0000

Data Index: 1637919 (Python Code)

Max Activating Token Index: 166

Text #6

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.8198. Min Act: -0.0000

Data Index: 1620342 (Python Code)

Max Activating Token Index: 207

Text #7

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.7440. Min Act: -0.0000

Data Index: 2676 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6771. Min Act: -0.0000

Data Index: 358273 (C4 (Web Text))

Max Activating Token Index: 571

Text #9

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.5909. Min Act: -0.0000

Data Index: 808316 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6595. Min Act: -0.0000

Data Index: 1342373 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.5774. Min Act: -0.0000

Data Index: 898608 (C4 (Web Text))

Max Activating Token Index: 797

Text #12

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6673. Min Act: -0.0000

Data Index: 571508 (C4 (Web Text))

Max Activating Token Index: 350

Text #13

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.7112. Min Act: -0.0000

Data Index: 273471 (C4 (Web Text))

Max Activating Token Index: 844

Text #14

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6489. Min Act: -0.0000

Data Index: 196535 (C4 (Web Text))

Max Activating Token Index: 742

Text #15

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6602. Min Act: -0.0000

Data Index: 1288942 (C4 (Web Text))

Max Activating Token Index: 612

Text #16

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.8956. Min Act: -0.0000

Data Index: 1351353 (C4 (Web Text))

Max Activating Token Index: 612

Text #17

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6823. Min Act: -0.0000

Data Index: 854543 (C4 (Web Text))

Max Activating Token Index: 820

Text #18

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6871. Min Act: -0.0000

Data Index: 1571775 (Python Code)

Max Activating Token Index: 902

Text #19

Max Range: 2.4632. Min Range: -2.4632

Max Act: 1.6740. Min Act: -0.0000

Data Index: 720500 (C4 (Web Text))

Max Activating Token Index: 603