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

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

Neuron 917 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.3492. Min Act: -0.0001

Data Index: 1024848 (C4 (Web Text))

Max Activating Token Index: 3

Text #1

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2583. Min Act: -0.0001

Data Index: 868374 (C4 (Web Text))

Max Activating Token Index: 484

Text #2

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2313. Min Act: -0.0002

Data Index: 586518 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2185. Min Act: -0.0001

Data Index: 470407 (C4 (Web Text))

Max Activating Token Index: 9

Text #4

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2081. Min Act: -0.0002

Data Index: 20852 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.2046. Min Act: -0.0002

Data Index: 103746 (C4 (Web Text))

Max Activating Token Index: 869

Text #6

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1929. Min Act: -0.0001

Data Index: 711759 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1914. Min Act: -0.0001

Data Index: 1599606 (Python Code)

Max Activating Token Index: 798

Text #8

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1765. Min Act: -0.0002

Data Index: 949368 (C4 (Web Text))

Max Activating Token Index: 365

Text #9

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1832. Min Act: -0.0002

Data Index: 1156583 (C4 (Web Text))

Max Activating Token Index: 228

Text #10

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1754. Min Act: -0.0001

Data Index: 1058959 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1676. Min Act: -0.0002

Data Index: 137473 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1773. Min Act: -0.0002

Data Index: 304120 (C4 (Web Text))

Max Activating Token Index: 126

Text #13

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1785. Min Act: -0.0001

Data Index: 589496 (C4 (Web Text))

Max Activating Token Index: 916

Text #14

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1741. Min Act: -0.0002

Data Index: 1122576 (C4 (Web Text))

Max Activating Token Index: 542

Text #15

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1672. Min Act: -0.0002

Data Index: 141704 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1714. Min Act: -0.0002

Data Index: 274509 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1681. Min Act: -0.0002

Data Index: 704411 (C4 (Web Text))

Max Activating Token Index: 304

Text #18

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1629. Min Act: -0.0002

Data Index: 644354 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.3492. Min Range: -0.3492

Max Act: 0.1651. Min Act: -0.0002

Data Index: 113228 (C4 (Web Text))

Max Activating Token Index: 871