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

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

Neuron 2800 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2791. Min Act: -0.0002

Data Index: 529422 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2732. Min Act: -0.0003

Data Index: 1196035 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2096. Min Act: -0.0002

Data Index: 933582 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2176. Min Act: -0.0002

Data Index: 469664 (C4 (Web Text))

Max Activating Token Index: 745

Text #4

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2075. Min Act: -0.0003

Data Index: 1049371 (C4 (Web Text))

Max Activating Token Index: 679

Text #5

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2261. Min Act: -0.0002

Data Index: 113123 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1848. Min Act: -0.0002

Data Index: 536237 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1981. Min Act: -0.0002

Data Index: 714022 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1873. Min Act: -0.0002

Data Index: 1308557 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.2070. Min Act: -0.0002

Data Index: 236024 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1910. Min Act: -0.0002

Data Index: 419995 (C4 (Web Text))

Max Activating Token Index: 694

Text #11

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1999. Min Act: -0.0002

Data Index: 1110180 (C4 (Web Text))

Max Activating Token Index: 556

Text #12

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1687. Min Act: -0.0002

Data Index: 423142 (C4 (Web Text))

Max Activating Token Index: 87

Text #13

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1822. Min Act: -0.0002

Data Index: 724527 (C4 (Web Text))

Max Activating Token Index: 107

Text #14

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1871. Min Act: -0.0002

Data Index: 149668 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1661. Min Act: -0.0002

Data Index: 523914 (C4 (Web Text))

Max Activating Token Index: 617

Text #16

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1733. Min Act: -0.0002

Data Index: 79819 (C4 (Web Text))

Max Activating Token Index: 738

Text #17

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1535. Min Act: -0.0002

Data Index: 640665 (C4 (Web Text))

Max Activating Token Index: 753

Text #18

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1568. Min Act: -0.0002

Data Index: 93919 (C4 (Web Text))

Max Activating Token Index: 513

Text #19

Max Range: 1.2791. Min Range: -1.2791

Max Act: 1.1625. Min Act: -0.0002

Data Index: 1084700 (C4 (Web Text))

Max Activating Token Index: 668