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

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

Neuron 3798 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.1772. Min Range: -6.1772

Max Act: 6.1772. Min Act: -0.0000

Data Index: 1039961 (C4 (Web Text))

Max Activating Token Index: 910

Text #1

Max Range: 6.1772. Min Range: -6.1772

Max Act: 5.6291. Min Act: -0.0000

Data Index: 657858 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 6.1772. Min Range: -6.1772

Max Act: 5.7388. Min Act: -0.0000

Data Index: 777985 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 6.1772. Min Range: -6.1772

Max Act: 5.0782. Min Act: -0.0000

Data Index: 763605 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.8650. Min Act: -0.0000

Data Index: 1255920 (C4 (Web Text))

Max Activating Token Index: 304

Text #5

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.8474. Min Act: -0.0000

Data Index: 497308 (C4 (Web Text))

Max Activating Token Index: 706

Text #6

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.9936. Min Act: -0.0000

Data Index: 1337783 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.9358. Min Act: -0.0000

Data Index: 457844 (C4 (Web Text))

Max Activating Token Index: 60

Text #8

Max Range: 6.1772. Min Range: -6.1772

Max Act: 5.3222. Min Act: -0.0000

Data Index: 747621 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.8850. Min Act: -0.0000

Data Index: 99782 (C4 (Web Text))

Max Activating Token Index: 277

Text #10

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.6163. Min Act: -0.0000

Data Index: 1202616 (C4 (Web Text))

Max Activating Token Index: 501

Text #11

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.8719. Min Act: -0.0000

Data Index: 603211 (C4 (Web Text))

Max Activating Token Index: 657

Text #12

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.6869. Min Act: -0.0000

Data Index: 530351 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.6958. Min Act: -0.0000

Data Index: 636095 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.5108. Min Act: -0.0000

Data Index: 886693 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.6944. Min Act: -0.0000

Data Index: 1091602 (C4 (Web Text))

Max Activating Token Index: 721

Text #16

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.3132. Min Act: -0.0000

Data Index: 709973 (C4 (Web Text))

Max Activating Token Index: 943

Text #17

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.6514. Min Act: -0.0000

Data Index: 391078 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.4509. Min Act: -0.0000

Data Index: 164151 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 6.1772. Min Range: -6.1772

Max Act: 4.6240. Min Act: -0.0000

Data Index: 53546 (C4 (Web Text))

Max Activating Token Index: 344