Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3159 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.8485. Min Act: -0.0000

Data Index: 692505 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.9050. Min Act: -0.0000

Data Index: 785417 (C4 (Web Text))

Max Activating Token Index: 725

Text #2

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7338. Min Act: -0.0000

Data Index: 948027 (C4 (Web Text))

Max Activating Token Index: 896

Text #3

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7846. Min Act: -0.0000

Data Index: 948346 (C4 (Web Text))

Max Activating Token Index: 751

Text #4

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6915. Min Act: -0.0000

Data Index: 919465 (C4 (Web Text))

Max Activating Token Index: 749

Text #5

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7639. Min Act: -0.0000

Data Index: 309926 (C4 (Web Text))

Max Activating Token Index: 738

Text #6

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.7010. Min Act: -0.0000

Data Index: 1521792 (Python Code)

Max Activating Token Index: 434

Text #7

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6012. Min Act: 0.0000

Data Index: 441136 (C4 (Web Text))

Max Activating Token Index: 755

Text #8

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6221. Min Act: -0.0000

Data Index: 869012 (C4 (Web Text))

Max Activating Token Index: 922

Text #9

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1260194 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1049349 (C4 (Web Text))

Max Activating Token Index: 707

Text #11

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.6024. Min Act: -0.0000

Data Index: 1444559 (Python Code)

Max Activating Token Index: 612

Text #12

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5666. Min Act: 0.0000

Data Index: 765540 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5528. Min Act: -0.0000

Data Index: 544512 (C4 (Web Text))

Max Activating Token Index: 760

Text #14

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5946. Min Act: -0.0000

Data Index: 1514974 (Python Code)

Max Activating Token Index: 360

Text #15

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5623. Min Act: -0.0000

Data Index: 611907 (C4 (Web Text))

Max Activating Token Index: 669

Text #16

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5697. Min Act: -0.0000

Data Index: 123426 (C4 (Web Text))

Max Activating Token Index: 917

Text #17

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5663. Min Act: 0.0000

Data Index: 1057085 (C4 (Web Text))

Max Activating Token Index: 243

Text #18

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5610. Min Act: -0.0000

Data Index: 396011 (C4 (Web Text))

Max Activating Token Index: 981

Text #19

Max Range: 0.9050. Min Range: -0.9050

Max Act: 0.5492. Min Act: -0.0000

Data Index: 1375689 (Python Code)

Max Activating Token Index: 742