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

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

Neuron 4146 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.3827. Min Range: -5.3827

Max Act: 5.3827. Min Act: -0.0000

Data Index: 1215915 (C4 (Web Text))

Max Activating Token Index: 604

Text #1

Max Range: 5.3827. Min Range: -5.3827

Max Act: 5.1611. Min Act: -0.0000

Data Index: 72230 (C4 (Web Text))

Max Activating Token Index: 807

Text #2

Max Range: 5.3827. Min Range: -5.3827

Max Act: 4.7405. Min Act: -0.0000

Data Index: 107868 (C4 (Web Text))

Max Activating Token Index: 902

Text #3

Max Range: 5.3827. Min Range: -5.3827

Max Act: 4.3157. Min Act: -0.0000

Data Index: 421446 (C4 (Web Text))

Max Activating Token Index: 110

Text #4

Max Range: 5.3827. Min Range: -5.3827

Max Act: 4.6164. Min Act: -0.0000

Data Index: 334452 (C4 (Web Text))

Max Activating Token Index: 870

Text #5

Max Range: 5.3827. Min Range: -5.3827

Max Act: 4.2460. Min Act: -0.0000

Data Index: 778823 (C4 (Web Text))

Max Activating Token Index: 255

Text #6

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.8454. Min Act: -0.0000

Data Index: 899487 (C4 (Web Text))

Max Activating Token Index: 312

Text #7

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.8601. Min Act: -0.0000

Data Index: 361780 (C4 (Web Text))

Max Activating Token Index: 404

Text #8

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.3619. Min Act: -0.0000

Data Index: 725267 (C4 (Web Text))

Max Activating Token Index: 968

Text #9

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.9671. Min Act: -0.0000

Data Index: 1073684 (C4 (Web Text))

Max Activating Token Index: 446

Text #10

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.6349. Min Act: -0.0000

Data Index: 127828 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.7672. Min Act: -0.0000

Data Index: 525861 (C4 (Web Text))

Max Activating Token Index: 310

Text #12

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.7432. Min Act: -0.0000

Data Index: 340247 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.8930. Min Act: -0.0000

Data Index: 73944 (C4 (Web Text))

Max Activating Token Index: 566

Text #14

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.5160. Min Act: -0.0000

Data Index: 38824 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.4807. Min Act: -0.0000

Data Index: 527769 (C4 (Web Text))

Max Activating Token Index: 620

Text #16

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.6252. Min Act: -0.0000

Data Index: 974715 (C4 (Web Text))

Max Activating Token Index: 39

Text #17

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.9117. Min Act: -0.0000

Data Index: 931552 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.4488. Min Act: -0.0000

Data Index: 1320839 (C4 (Web Text))

Max Activating Token Index: 663

Text #19

Max Range: 5.3827. Min Range: -5.3827

Max Act: 3.5968. Min Act: -0.0000

Data Index: 1187529 (C4 (Web Text))

Max Activating Token Index: 117