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

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

Neuron 21 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1890. Min Act: -0.0000

Data Index: 833046 (C4 (Web Text))

Max Activating Token Index: 787

Text #1

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1629. Min Act: -0.0000

Data Index: 1055212 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1370. Min Act: -0.0000

Data Index: 1205341 (C4 (Web Text))

Max Activating Token Index: 286

Text #3

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.1672. Min Act: -0.0000

Data Index: 1101248 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0009. Min Act: -0.0000

Data Index: 708713 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0885. Min Act: -0.0000

Data Index: 1194642 (C4 (Web Text))

Max Activating Token Index: 190

Text #6

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0203. Min Act: -0.0000

Data Index: 401877 (C4 (Web Text))

Max Activating Token Index: 356

Text #7

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9750. Min Act: 0.0000

Data Index: 765140 (C4 (Web Text))

Max Activating Token Index: 758

Text #8

Max Range: 1.1890. Min Range: -1.1890

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1272518 (C4 (Web Text))

Max Activating Token Index: 623

Text #9

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9739. Min Act: -0.0000

Data Index: 58347 (C4 (Web Text))

Max Activating Token Index: 107

Text #10

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9732. Min Act: -0.0000

Data Index: 688952 (C4 (Web Text))

Max Activating Token Index: 846

Text #11

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9287. Min Act: 0.0000

Data Index: 1041340 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9804. Min Act: -0.0000

Data Index: 562831 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9511. Min Act: -0.0000

Data Index: 1158352 (C4 (Web Text))

Max Activating Token Index: 426

Text #14

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9529. Min Act: -0.0000

Data Index: 944783 (C4 (Web Text))

Max Activating Token Index: 817

Text #15

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9608. Min Act: -0.0000

Data Index: 675153 (C4 (Web Text))

Max Activating Token Index: 698

Text #16

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8819. Min Act: 0.0000

Data Index: 712551 (C4 (Web Text))

Max Activating Token Index: 898

Text #17

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8528. Min Act: -0.0000

Data Index: 277079 (C4 (Web Text))

Max Activating Token Index: 520

Text #18

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.9016. Min Act: 0.0000

Data Index: 74000 (C4 (Web Text))

Max Activating Token Index: 1016

Text #19

Max Range: 1.1890. Min Range: -1.1890

Max Act: 0.8544. Min Act: -0.0000

Data Index: 62693 (C4 (Web Text))

Max Activating Token Index: 272