Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1867 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3753. Min Act: -0.0001

Data Index: 1055296 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3889. Min Act: -0.0001

Data Index: 798178 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3794. Min Act: -0.0001

Data Index: 1005002 (C4 (Web Text))

Max Activating Token Index: 291

Text #3

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3765. Min Act: -0.0001

Data Index: 1268138 (C4 (Web Text))

Max Activating Token Index: 885

Text #4

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3699. Min Act: -0.0001

Data Index: 625377 (C4 (Web Text))

Max Activating Token Index: 403

Text #5

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3406. Min Act: -0.0001

Data Index: 1292092 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3633. Min Act: -0.0001

Data Index: 898438 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3739. Min Act: -0.0001

Data Index: 744936 (C4 (Web Text))

Max Activating Token Index: 708

Text #8

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3598. Min Act: -0.0001

Data Index: 1083895 (C4 (Web Text))

Max Activating Token Index: 926

Text #9

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3467. Min Act: -0.0001

Data Index: 437279 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3542. Min Act: -0.0001

Data Index: 716191 (C4 (Web Text))

Max Activating Token Index: 888

Text #11

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3237. Min Act: -0.0001

Data Index: 382849 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3532. Min Act: -0.0001

Data Index: 7285 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3441. Min Act: -0.0001

Data Index: 655168 (C4 (Web Text))

Max Activating Token Index: 912

Text #14

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3499. Min Act: -0.0001

Data Index: 984126 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3328. Min Act: -0.0001

Data Index: 533344 (C4 (Web Text))

Max Activating Token Index: 688

Text #16

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3618. Min Act: -0.0001

Data Index: 952324 (C4 (Web Text))

Max Activating Token Index: 812

Text #17

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3413. Min Act: -0.0001

Data Index: 1050726 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3502. Min Act: -0.0001

Data Index: 396288 (C4 (Web Text))

Max Activating Token Index: 523

Text #19

Max Range: 0.3889. Min Range: -0.3889

Max Act: 0.3389. Min Act: -0.0001

Data Index: 978677 (C4 (Web Text))

Max Activating Token Index: 714