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

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

Neuron 317 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.4024. Min Act: -0.0001

Data Index: 447003 (C4 (Web Text))

Max Activating Token Index: 501

Text #1

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1063. Min Act: -0.0001

Data Index: 809510 (C4 (Web Text))

Max Activating Token Index: 971

Text #2

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1021. Min Act: -0.0001

Data Index: 830727 (C4 (Web Text))

Max Activating Token Index: 372

Text #3

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.1030. Min Act: -0.0001

Data Index: 824812 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0928. Min Act: -0.0001

Data Index: 198408 (C4 (Web Text))

Max Activating Token Index: 738

Text #5

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0555. Min Act: -0.0001

Data Index: 238786 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0804. Min Act: -0.0001

Data Index: 59835 (C4 (Web Text))

Max Activating Token Index: 830

Text #7

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0284. Min Act: -0.0001

Data Index: 785822 (C4 (Web Text))

Max Activating Token Index: 739

Text #8

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0634. Min Act: -0.0001

Data Index: 905957 (C4 (Web Text))

Max Activating Token Index: 787

Text #9

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0253. Min Act: -0.0001

Data Index: 1007777 (C4 (Web Text))

Max Activating Token Index: 568

Text #10

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0106. Min Act: -0.0001

Data Index: 199421 (C4 (Web Text))

Max Activating Token Index: 964

Text #11

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0898. Min Act: -0.0001

Data Index: 203176 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0563. Min Act: -0.0001

Data Index: 81102 (C4 (Web Text))

Max Activating Token Index: 813

Text #13

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0703. Min Act: -0.0001

Data Index: 266335 (C4 (Web Text))

Max Activating Token Index: 650

Text #14

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0533. Min Act: -0.0001

Data Index: 1211499 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0683. Min Act: -0.0001

Data Index: 1091189 (C4 (Web Text))

Max Activating Token Index: 916

Text #16

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0122. Min Act: -0.0001

Data Index: 132303 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.4024. Min Range: -1.4024

Max Act: 1.0006. Min Act: -0.0001

Data Index: 240136 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.4024. Min Range: -1.4024

Max Act: 0.9680. Min Act: -0.0001

Data Index: 494468 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 1.4024. Min Range: -1.4024

Max Act: 0.9721. Min Act: -0.0001

Data Index: 130663 (C4 (Web Text))

Max Activating Token Index: 383