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

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

Neuron 4832 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.5818. Min Act: -0.0000

Data Index: 336401 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.4792. Min Act: -0.0000

Data Index: 604716 (C4 (Web Text))

Max Activating Token Index: 799

Text #2

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.4573. Min Act: -0.0000

Data Index: 643307 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3311. Min Act: -0.0000

Data Index: 575536 (C4 (Web Text))

Max Activating Token Index: 708

Text #4

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.4708. Min Act: -0.0000

Data Index: 1244674 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3292. Min Act: -0.0000

Data Index: 1200579 (C4 (Web Text))

Max Activating Token Index: 148

Text #6

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3455. Min Act: -0.0000

Data Index: 1181045 (C4 (Web Text))

Max Activating Token Index: 99

Text #7

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.1808. Min Act: -0.0000

Data Index: 1269296 (C4 (Web Text))

Max Activating Token Index: 72

Text #8

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.1498. Min Act: -0.0000

Data Index: 870637 (C4 (Web Text))

Max Activating Token Index: 328

Text #9

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.1448. Min Act: -0.0000

Data Index: 438778 (C4 (Web Text))

Max Activating Token Index: 114

Text #10

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.3509. Min Act: -0.0000

Data Index: 430834 (C4 (Web Text))

Max Activating Token Index: 473

Text #11

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.2102. Min Act: -0.0000

Data Index: 428825 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.2008. Min Act: -0.0000

Data Index: 169799 (C4 (Web Text))

Max Activating Token Index: 43

Text #13

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.2029. Min Act: -0.0000

Data Index: 1005756 (C4 (Web Text))

Max Activating Token Index: 476

Text #14

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.1931. Min Act: -0.0000

Data Index: 1142801 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.1881. Min Act: -0.0000

Data Index: 469949 (C4 (Web Text))

Max Activating Token Index: 35

Text #16

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.0612. Min Act: -0.0000

Data Index: 999872 (C4 (Web Text))

Max Activating Token Index: 89

Text #17

Max Range: 2.5818. Min Range: -2.5818

Max Act: 1.9304. Min Act: -0.0000

Data Index: 903865 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.1603. Min Act: -0.0000

Data Index: 483784 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 2.5818. Min Range: -2.5818

Max Act: 2.0375. Min Act: -0.0000

Data Index: 4252 (C4 (Web Text))

Max Activating Token Index: 846