Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1277 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0974. Min Act: -0.0000

Data Index: 1319985 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0873. Min Act: -0.0001

Data Index: 1319046 (C4 (Web Text))

Max Activating Token Index: 1011

Text #2

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1073394 (C4 (Web Text))

Max Activating Token Index: 755

Text #3

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0821. Min Act: -0.0001

Data Index: 1260188 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0787. Min Act: -0.0001

Data Index: 1090500 (C4 (Web Text))

Max Activating Token Index: 312

Text #5

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0807. Min Act: -0.0001

Data Index: 230345 (C4 (Web Text))

Max Activating Token Index: 900

Text #6

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0769. Min Act: -0.0001

Data Index: 469229 (C4 (Web Text))

Max Activating Token Index: 682

Text #7

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0782. Min Act: -0.0001

Data Index: 963642 (C4 (Web Text))

Max Activating Token Index: 810

Text #8

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0732. Min Act: -0.0000

Data Index: 626632 (C4 (Web Text))

Max Activating Token Index: 632

Text #9

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0758. Min Act: -0.0001

Data Index: 1188062 (C4 (Web Text))

Max Activating Token Index: 724

Text #10

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0773. Min Act: -0.0001

Data Index: 287228 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0794. Min Act: -0.0000

Data Index: 16685 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0738. Min Act: -0.0001

Data Index: 811729 (C4 (Web Text))

Max Activating Token Index: 820

Text #13

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0743. Min Act: -0.0001

Data Index: 791974 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0729. Min Act: -0.0001

Data Index: 409383 (C4 (Web Text))

Max Activating Token Index: 747

Text #15

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0640. Min Act: -0.0001

Data Index: 820227 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0694. Min Act: -0.0001

Data Index: 660180 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0734. Min Act: -0.0000

Data Index: 479137 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0736. Min Act: -0.0001

Data Index: 523528 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 0.0974. Min Range: -0.0974

Max Act: 0.0696. Min Act: -0.0000

Data Index: 348581 (C4 (Web Text))

Max Activating Token Index: 674