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

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

Neuron 3604 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: 2.1762. Min Range: -2.1762

Max Act: 2.1762. Min Act: -0.0000

Data Index: 510519 (C4 (Web Text))

Max Activating Token Index: 770

Text #1

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.8128. Min Act: -0.0000

Data Index: 218661 (C4 (Web Text))

Max Activating Token Index: 14

Text #2

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.7823. Min Act: -0.0000

Data Index: 854925 (C4 (Web Text))

Max Activating Token Index: 1010

Text #3

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.8614. Min Act: -0.0000

Data Index: 959303 (C4 (Web Text))

Max Activating Token Index: 803

Text #4

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.7093. Min Act: -0.0000

Data Index: 653877 (C4 (Web Text))

Max Activating Token Index: 152

Text #5

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.4980. Min Act: -0.0001

Data Index: 157615 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.6667. Min Act: -0.0001

Data Index: 577234 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.6028. Min Act: -0.0000

Data Index: 1276349 (C4 (Web Text))

Max Activating Token Index: 811

Text #8

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.4903. Min Act: -0.0000

Data Index: 379028 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.5827. Min Act: -0.0000

Data Index: 1126922 (C4 (Web Text))

Max Activating Token Index: 943

Text #10

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.7157. Min Act: -0.0000

Data Index: 329218 (C4 (Web Text))

Max Activating Token Index: 497

Text #11

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.6750. Min Act: -0.0000

Data Index: 922965 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.6042. Min Act: -0.0001

Data Index: 192451 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.5835. Min Act: -0.0000

Data Index: 411121 (C4 (Web Text))

Max Activating Token Index: 752

Text #14

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.6021. Min Act: -0.0000

Data Index: 369732 (C4 (Web Text))

Max Activating Token Index: 438

Text #15

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.7759. Min Act: -0.0000

Data Index: 711564 (C4 (Web Text))

Max Activating Token Index: 734

Text #16

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.6652. Min Act: -0.0000

Data Index: 1032877 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.4934. Min Act: -0.0001

Data Index: 266340 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.5604. Min Act: -0.0001

Data Index: 523978 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 2.1762. Min Range: -2.1762

Max Act: 1.5634. Min Act: -0.0000

Data Index: 1283708 (C4 (Web Text))

Max Activating Token Index: 19