Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3920 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.1408. Min Act: -0.0000

Data Index: 424008 (C4 (Web Text))

Max Activating Token Index: 352

Text #1

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0951. Min Act: -0.0000

Data Index: 119770 (C4 (Web Text))

Max Activating Token Index: 701

Text #2

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0886. Min Act: -0.0000

Data Index: 760073 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1183600 (C4 (Web Text))

Max Activating Token Index: 592

Text #4

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0875. Min Act: -0.0000

Data Index: 153159 (C4 (Web Text))

Max Activating Token Index: 246

Text #5

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0806. Min Act: -0.0000

Data Index: 831855 (C4 (Web Text))

Max Activating Token Index: 839

Text #6

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0802. Min Act: -0.0000

Data Index: 892815 (C4 (Web Text))

Max Activating Token Index: 955

Text #7

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0801. Min Act: -0.0000

Data Index: 473414 (C4 (Web Text))

Max Activating Token Index: 160

Text #8

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0797. Min Act: -0.0000

Data Index: 594961 (C4 (Web Text))

Max Activating Token Index: 774

Text #9

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0794. Min Act: -0.0001

Data Index: 242208 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0783. Min Act: -0.0000

Data Index: 153988 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0773. Min Act: -0.0001

Data Index: 1228084 (C4 (Web Text))

Max Activating Token Index: 485

Text #12

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1222256 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0741. Min Act: -0.0001

Data Index: 128790 (C4 (Web Text))

Max Activating Token Index: 977

Text #14

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0791. Min Act: -0.0001

Data Index: 1208831 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0735. Min Act: -0.0000

Data Index: 704344 (C4 (Web Text))

Max Activating Token Index: 618

Text #16

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0733. Min Act: -0.0000

Data Index: 826507 (C4 (Web Text))

Max Activating Token Index: 419

Text #17

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0683. Min Act: -0.0001

Data Index: 1541518 (Python Code)

Max Activating Token Index: 720

Text #18

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0730. Min Act: -0.0000

Data Index: 444147 (C4 (Web Text))

Max Activating Token Index: 858

Text #19

Max Range: 0.1408. Min Range: -0.1408

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1034321 (C4 (Web Text))

Max Activating Token Index: 445