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

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

Neuron 4876 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.5208. Min Act: -0.0000

Data Index: 509774 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.5381. Min Act: -0.0001

Data Index: 1505275 (Python Code)

Max Activating Token Index: 964

Text #2

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.4475. Min Act: -0.0000

Data Index: 270998 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1856. Min Act: -0.0001

Data Index: 1553657 (Python Code)

Max Activating Token Index: 658

Text #4

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1922. Min Act: -0.0001

Data Index: 1003425 (C4 (Web Text))

Max Activating Token Index: 4

Text #5

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1074. Min Act: -0.0000

Data Index: 811858 (C4 (Web Text))

Max Activating Token Index: 4

Text #6

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1605. Min Act: -0.0001

Data Index: 1371126 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0324. Min Act: -0.0001

Data Index: 1446347 (Python Code)

Max Activating Token Index: 835

Text #8

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0906. Min Act: -0.0001

Data Index: 1556058 (Python Code)

Max Activating Token Index: 487

Text #9

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.1052. Min Act: -0.0000

Data Index: 1258344 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0652. Min Act: -0.0001

Data Index: 1595603 (Python Code)

Max Activating Token Index: 591

Text #11

Max Range: 1.5381. Min Range: -1.5381

Max Act: 0.9953. Min Act: -0.0001

Data Index: 447443 (C4 (Web Text))

Max Activating Token Index: 658

Text #12

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0761. Min Act: -0.0001

Data Index: 1364193 (Python Code)

Max Activating Token Index: 893

Text #13

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0134. Min Act: -0.0000

Data Index: 43624 (C4 (Web Text))

Max Activating Token Index: 136

Text #14

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0875. Min Act: -0.0001

Data Index: 1620127 (Python Code)

Max Activating Token Index: 673

Text #15

Max Range: 1.5381. Min Range: -1.5381

Max Act: 0.9723. Min Act: -0.0000

Data Index: 461441 (C4 (Web Text))

Max Activating Token Index: 349

Text #16

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0420. Min Act: -0.0001

Data Index: 102192 (C4 (Web Text))

Max Activating Token Index: 706

Text #17

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0658. Min Act: -0.0000

Data Index: 111384 (C4 (Web Text))

Max Activating Token Index: 551

Text #18

Max Range: 1.5381. Min Range: -1.5381

Max Act: 1.0370. Min Act: -0.0000

Data Index: 1028748 (C4 (Web Text))

Max Activating Token Index: 723

Text #19

Max Range: 1.5381. Min Range: -1.5381

Max Act: 0.9995. Min Act: -0.0001

Data Index: 1473940 (Python Code)

Max Activating Token Index: 760