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

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

Neuron 3107 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7866. Min Range: -1.7866

Max Act: 1.7866. Min Act: -0.0000

Data Index: 1316346 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.7866. Min Range: -1.7866

Max Act: 1.1966. Min Act: -0.0000

Data Index: 205366 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.7866. Min Range: -1.7866

Max Act: 1.0155. Min Act: -0.0000

Data Index: 426240 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9762. Min Act: -0.0000

Data Index: 721055 (C4 (Web Text))

Max Activating Token Index: 575

Text #4

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9792. Min Act: -0.0000

Data Index: 875073 (C4 (Web Text))

Max Activating Token Index: 334

Text #5

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9573. Min Act: -0.0000

Data Index: 398892 (C4 (Web Text))

Max Activating Token Index: 439

Text #6

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8863. Min Act: -0.0000

Data Index: 1080500 (C4 (Web Text))

Max Activating Token Index: 455

Text #7

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9258. Min Act: -0.0000

Data Index: 1077864 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9061. Min Act: -0.0000

Data Index: 1215832 (C4 (Web Text))

Max Activating Token Index: 736

Text #9

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.9002. Min Act: -0.0000

Data Index: 255202 (C4 (Web Text))

Max Activating Token Index: 572

Text #10

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8812. Min Act: -0.0000

Data Index: 270267 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8200. Min Act: -0.0000

Data Index: 932202 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8912. Min Act: -0.0000

Data Index: 41649 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.7944. Min Act: -0.0000

Data Index: 176883 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.7463. Min Act: -0.0000

Data Index: 1023744 (C4 (Web Text))

Max Activating Token Index: 1016

Text #15

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.7262. Min Act: -0.0000

Data Index: 376502 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.7703. Min Act: -0.0000

Data Index: 499175 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.8802. Min Act: -0.0000

Data Index: 123032 (C4 (Web Text))

Max Activating Token Index: 155

Text #18

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.7451. Min Act: -0.0000

Data Index: 221983 (C4 (Web Text))

Max Activating Token Index: 575

Text #19

Max Range: 1.7866. Min Range: -1.7866

Max Act: 0.7684. Min Act: -0.0000

Data Index: 592864 (C4 (Web Text))

Max Activating Token Index: 683