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

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

Neuron 3676 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4730. Min Act: -0.0000

Data Index: 1476106 (Python Code)

Max Activating Token Index: 824

Text #1

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4470. Min Act: -0.0000

Data Index: 234927 (C4 (Web Text))

Max Activating Token Index: 574

Text #2

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4557. Min Act: -0.0000

Data Index: 1065084 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3580. Min Act: -0.0000

Data Index: 233617 (C4 (Web Text))

Max Activating Token Index: 590

Text #4

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.4038. Min Act: -0.0000

Data Index: 94936 (C4 (Web Text))

Max Activating Token Index: 995

Text #5

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3700. Min Act: -0.0000

Data Index: 190826 (C4 (Web Text))

Max Activating Token Index: 978

Text #6

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3208. Min Act: -0.0000

Data Index: 1268212 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3379. Min Act: -0.0000

Data Index: 1206737 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3563. Min Act: -0.0000

Data Index: 960691 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3362. Min Act: -0.0000

Data Index: 108840 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3368. Min Act: -0.0000

Data Index: 875960 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3569. Min Act: -0.0000

Data Index: 441750 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3366. Min Act: -0.0000

Data Index: 470957 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3305. Min Act: -0.0000

Data Index: 556864 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3719. Min Act: -0.0000

Data Index: 1310416 (C4 (Web Text))

Max Activating Token Index: 524

Text #15

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3219. Min Act: -0.0000

Data Index: 104780 (C4 (Web Text))

Max Activating Token Index: 215

Text #16

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1018107 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3452. Min Act: -0.0000

Data Index: 1016773 (C4 (Web Text))

Max Activating Token Index: 440

Text #18

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3258. Min Act: -0.0000

Data Index: 644545 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 0.4730. Min Range: -0.4730

Max Act: 0.3240. Min Act: -0.0000

Data Index: 28574 (C4 (Web Text))

Max Activating Token Index: 822