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

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

Neuron 1762 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8057. Min Act: -0.0000

Data Index: 875178 (C4 (Web Text))

Max Activating Token Index: 44

Text #1

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8518. Min Act: -0.0000

Data Index: 923192 (C4 (Web Text))

Max Activating Token Index: 349

Text #2

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8697. Min Act: -0.0000

Data Index: 163139 (C4 (Web Text))

Max Activating Token Index: 952

Text #3

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8688. Min Act: -0.0000

Data Index: 480990 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7296. Min Act: -0.0000

Data Index: 518599 (C4 (Web Text))

Max Activating Token Index: 710

Text #5

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.8652. Min Act: -0.0000

Data Index: 555768 (C4 (Web Text))

Max Activating Token Index: 53

Text #6

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7033. Min Act: -0.0000

Data Index: 928544 (C4 (Web Text))

Max Activating Token Index: 77

Text #7

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7167. Min Act: -0.0001

Data Index: 176103 (C4 (Web Text))

Max Activating Token Index: 741

Text #8

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7047. Min Act: -0.0001

Data Index: 874707 (C4 (Web Text))

Max Activating Token Index: 425

Text #9

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.7349. Min Act: -0.0000

Data Index: 520495 (C4 (Web Text))

Max Activating Token Index: 1003

Text #10

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6412. Min Act: -0.0001

Data Index: 588010 (C4 (Web Text))

Max Activating Token Index: 359

Text #11

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5892. Min Act: -0.0000

Data Index: 209884 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6079. Min Act: -0.0000

Data Index: 621109 (C4 (Web Text))

Max Activating Token Index: 557

Text #13

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5814. Min Act: -0.0001

Data Index: 597089 (C4 (Web Text))

Max Activating Token Index: 757

Text #14

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6155. Min Act: -0.0000

Data Index: 972545 (C4 (Web Text))

Max Activating Token Index: 881

Text #15

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6732. Min Act: -0.0000

Data Index: 477601 (C4 (Web Text))

Max Activating Token Index: 562

Text #16

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1224951 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5934. Min Act: -0.0000

Data Index: 1153157 (C4 (Web Text))

Max Activating Token Index: 108

Text #18

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.4346. Min Act: -0.0000

Data Index: 354722 (C4 (Web Text))

Max Activating Token Index: 117

Text #19

Max Range: 0.8697. Min Range: -0.8697

Max Act: 0.5057. Min Act: -0.0000

Data Index: 890628 (C4 (Web Text))

Max Activating Token Index: 100