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

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

Neuron 4628 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.9702. Min Act: -0.0000

Data Index: 1350194 (C4 (Web Text))

Max Activating Token Index: 410

Text #1

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2712. Min Act: -0.0000

Data Index: 1039675 (C4 (Web Text))

Max Activating Token Index: 917

Text #2

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.2725. Min Act: -0.0000

Data Index: 1016756 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.9962. Min Act: -0.0000

Data Index: 1171887 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.0405. Min Act: -0.0000

Data Index: 1005912 (C4 (Web Text))

Max Activating Token Index: 401

Text #5

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.1037. Min Act: -0.0000

Data Index: 355991 (C4 (Web Text))

Max Activating Token Index: 477

Text #6

Max Range: 2.9702. Min Range: -2.9702

Max Act: 2.1524. Min Act: -0.0000

Data Index: 1068999 (C4 (Web Text))

Max Activating Token Index: 665

Text #7

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.9706. Min Act: -0.0000

Data Index: 732051 (C4 (Web Text))

Max Activating Token Index: 775

Text #8

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.9036. Min Act: -0.0000

Data Index: 615803 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.7715. Min Act: -0.0000

Data Index: 546962 (C4 (Web Text))

Max Activating Token Index: 994

Text #10

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.6972. Min Act: -0.0000

Data Index: 984865 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.6033. Min Act: -0.0000

Data Index: 1290176 (C4 (Web Text))

Max Activating Token Index: 950

Text #12

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.7942. Min Act: -0.0000

Data Index: 1349204 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.6857. Min Act: -0.0000

Data Index: 1112873 (C4 (Web Text))

Max Activating Token Index: 769

Text #14

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.6798. Min Act: -0.0000

Data Index: 134639 (C4 (Web Text))

Max Activating Token Index: 901

Text #15

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.6753. Min Act: -0.0000

Data Index: 171012 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.7656. Min Act: -0.0001

Data Index: 176051 (C4 (Web Text))

Max Activating Token Index: 435

Text #17

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.7590. Min Act: -0.0000

Data Index: 594546 (C4 (Web Text))

Max Activating Token Index: 963

Text #18

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.7325. Min Act: -0.0000

Data Index: 1208134 (C4 (Web Text))

Max Activating Token Index: 365

Text #19

Max Range: 2.9702. Min Range: -2.9702

Max Act: 1.5753. Min Act: -0.0000

Data Index: 329003 (C4 (Web Text))

Max Activating Token Index: 171