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

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

Neuron 6081 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1728. Min Range: -1.1728

Max Act: 1.1728. Min Act: -0.0000

Data Index: 958475 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 1.1728. Min Range: -1.1728

Max Act: 1.0610. Min Act: -0.0000

Data Index: 383629 (C4 (Web Text))

Max Activating Token Index: 859

Text #2

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9828. Min Act: -0.0000

Data Index: 960221 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9602. Min Act: -0.0000

Data Index: 74128 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 1.1728. Min Range: -1.1728

Max Act: 1.0768. Min Act: -0.0000

Data Index: 581582 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9160. Min Act: -0.0000

Data Index: 808645 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9541. Min Act: -0.0000

Data Index: 1239526 (C4 (Web Text))

Max Activating Token Index: 912

Text #7

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9049. Min Act: -0.0000

Data Index: 958690 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9479. Min Act: -0.0000

Data Index: 944582 (C4 (Web Text))

Max Activating Token Index: 668

Text #9

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9379. Min Act: -0.0000

Data Index: 1209509 (C4 (Web Text))

Max Activating Token Index: 89

Text #10

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8900. Min Act: -0.0000

Data Index: 584010 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9016. Min Act: -0.0000

Data Index: 220255 (C4 (Web Text))

Max Activating Token Index: 605

Text #12

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1606678 (Python Code)

Max Activating Token Index: 1016

Text #13

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8949. Min Act: -0.0000

Data Index: 693366 (C4 (Web Text))

Max Activating Token Index: 791

Text #14

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9489. Min Act: -0.0000

Data Index: 158711 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.9293. Min Act: -0.0000

Data Index: 60099 (C4 (Web Text))

Max Activating Token Index: 243

Text #16

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8904. Min Act: -0.0000

Data Index: 1243229 (C4 (Web Text))

Max Activating Token Index: 288

Text #17

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8891. Min Act: -0.0000

Data Index: 983090 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8804. Min Act: 0.0000

Data Index: 178642 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 1.1728. Min Range: -1.1728

Max Act: 0.8664. Min Act: -0.0000

Data Index: 1056402 (C4 (Web Text))

Max Activating Token Index: 103