Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 828 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3892. Min Act: -0.0000

Data Index: 129714 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3660. Min Act: -0.0000

Data Index: 789538 (C4 (Web Text))

Max Activating Token Index: 348

Text #2

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3180. Min Act: -0.0000

Data Index: 1149753 (C4 (Web Text))

Max Activating Token Index: 539

Text #3

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3174. Min Act: -0.0000

Data Index: 54765 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3117. Min Act: -0.0000

Data Index: 147321 (C4 (Web Text))

Max Activating Token Index: 736

Text #5

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3108. Min Act: -0.0000

Data Index: 667336 (C4 (Web Text))

Max Activating Token Index: 474

Text #6

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3086. Min Act: -0.0000

Data Index: 795151 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.3032. Min Act: -0.0000

Data Index: 953333 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2834. Min Act: 0.0000

Data Index: 832937 (C4 (Web Text))

Max Activating Token Index: 927

Text #9

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2757. Min Act: -0.0000

Data Index: 888460 (C4 (Web Text))

Max Activating Token Index: 769

Text #10

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2746. Min Act: -0.0000

Data Index: 1172962 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2662. Min Act: -0.0000

Data Index: 1198396 (C4 (Web Text))

Max Activating Token Index: 937

Text #12

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2788. Min Act: -0.0000

Data Index: 278082 (C4 (Web Text))

Max Activating Token Index: 235

Text #13

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2901. Min Act: -0.0000

Data Index: 539199 (C4 (Web Text))

Max Activating Token Index: 196

Text #14

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2714. Min Act: -0.0000

Data Index: 147906 (C4 (Web Text))

Max Activating Token Index: 433

Text #15

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2606. Min Act: -0.0000

Data Index: 427691 (C4 (Web Text))

Max Activating Token Index: 956

Text #16

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2720. Min Act: -0.0000

Data Index: 353144 (C4 (Web Text))

Max Activating Token Index: 54

Text #17

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2473. Min Act: -0.0000

Data Index: 519356 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2562. Min Act: -0.0000

Data Index: 53406 (C4 (Web Text))

Max Activating Token Index: 495

Text #19

Max Range: 0.3892. Min Range: -0.3892

Max Act: 0.2758. Min Act: -0.0000

Data Index: 928206 (C4 (Web Text))

Max Activating Token Index: 891