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

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

Neuron 3267 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.3021. Min Act: -0.0001

Data Index: 401696 (C4 (Web Text))

Max Activating Token Index: 72

Text #1

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.1618. Min Act: -0.0001

Data Index: 321046 (C4 (Web Text))

Max Activating Token Index: 41

Text #2

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.1507. Min Act: -0.0001

Data Index: 297741 (C4 (Web Text))

Max Activating Token Index: 456

Text #3

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0796. Min Act: -0.0001

Data Index: 1040486 (C4 (Web Text))

Max Activating Token Index: 939

Text #4

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.1345. Min Act: -0.0001

Data Index: 270757 (C4 (Web Text))

Max Activating Token Index: 750

Text #5

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.1158. Min Act: -0.0001

Data Index: 805555 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0940. Min Act: -0.0001

Data Index: 1025734 (C4 (Web Text))

Max Activating Token Index: 19

Text #7

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0922. Min Act: -0.0001

Data Index: 1223907 (C4 (Web Text))

Max Activating Token Index: 464

Text #8

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.1915. Min Act: -0.0001

Data Index: 429522 (C4 (Web Text))

Max Activating Token Index: 963

Text #9

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0648. Min Act: -0.0001

Data Index: 534613 (C4 (Web Text))

Max Activating Token Index: 746

Text #10

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0510. Min Act: -0.0001

Data Index: 455025 (C4 (Web Text))

Max Activating Token Index: 280

Text #11

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0469. Min Act: -0.0001

Data Index: 1175753 (C4 (Web Text))

Max Activating Token Index: 908

Text #12

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0734. Min Act: -0.0001

Data Index: 1342256 (C4 (Web Text))

Max Activating Token Index: 919

Text #13

Max Range: 1.3021. Min Range: -1.3021

Max Act: 1.0457. Min Act: -0.0001

Data Index: 496567 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9722. Min Act: -0.0001

Data Index: 425161 (C4 (Web Text))

Max Activating Token Index: 995

Text #15

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9576. Min Act: -0.0001

Data Index: 540931 (C4 (Web Text))

Max Activating Token Index: 16

Text #16

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9518. Min Act: -0.0001

Data Index: 379633 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.8950. Min Act: -0.0001

Data Index: 434991 (C4 (Web Text))

Max Activating Token Index: 606

Text #18

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9765. Min Act: -0.0001

Data Index: 162581 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.3021. Min Range: -1.3021

Max Act: 0.9419. Min Act: -0.0001

Data Index: 642010 (C4 (Web Text))

Max Activating Token Index: 513