Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2040 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.5891. Min Act: -0.0001

Data Index: 448615 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.4261. Min Act: -0.0001

Data Index: 444148 (C4 (Web Text))

Max Activating Token Index: 1003

Text #2

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3550. Min Act: -0.0001

Data Index: 1029461 (C4 (Web Text))

Max Activating Token Index: 540

Text #3

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.5304. Min Act: -0.0001

Data Index: 31636 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.5842. Min Act: -0.0002

Data Index: 91722 (C4 (Web Text))

Max Activating Token Index: 936

Text #5

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3646. Min Act: -0.0002

Data Index: 515993 (C4 (Web Text))

Max Activating Token Index: 613

Text #6

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3332. Min Act: -0.0001

Data Index: 591126 (C4 (Web Text))

Max Activating Token Index: 584

Text #7

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.4348. Min Act: -0.0001

Data Index: 697324 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3879. Min Act: -0.0001

Data Index: 113802 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3781. Min Act: -0.0002

Data Index: 627861 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.2930. Min Act: -0.0001

Data Index: 760593 (C4 (Web Text))

Max Activating Token Index: 995

Text #11

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.4075. Min Act: -0.0001

Data Index: 1130800 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3845. Min Act: -0.0001

Data Index: 1180301 (C4 (Web Text))

Max Activating Token Index: 962

Text #13

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.2784. Min Act: -0.0002

Data Index: 1770 (C4 (Web Text))

Max Activating Token Index: 144

Text #14

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3591. Min Act: -0.0001

Data Index: 1241404 (C4 (Web Text))

Max Activating Token Index: 644

Text #15

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3502. Min Act: -0.0002

Data Index: 990179 (C4 (Web Text))

Max Activating Token Index: 388

Text #16

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.4056. Min Act: -0.0002

Data Index: 291695 (C4 (Web Text))

Max Activating Token Index: 1018

Text #17

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3353. Min Act: -0.0001

Data Index: 1296596 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.2482. Min Act: -0.0002

Data Index: 464553 (C4 (Web Text))

Max Activating Token Index: 94

Text #19

Max Range: 1.5891. Min Range: -1.5891

Max Act: 1.3320. Min Act: -0.0002

Data Index: 104484 (C4 (Web Text))

Max Activating Token Index: 756