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

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

Neuron 5106 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 6.5175. Min Range: -6.5175

Max Act: 6.5175. Min Act: -0.0000

Data Index: 166078 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.7455. Min Act: -0.0000

Data Index: 634679 (C4 (Web Text))

Max Activating Token Index: 817

Text #2

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.7035. Min Act: -0.0000

Data Index: 1284161 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.6561. Min Act: -0.0000

Data Index: 755279 (C4 (Web Text))

Max Activating Token Index: 104

Text #4

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.4631. Min Act: -0.0000

Data Index: 226647 (C4 (Web Text))

Max Activating Token Index: 722

Text #5

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.2308. Min Act: -0.0000

Data Index: 842748 (C4 (Web Text))

Max Activating Token Index: 531

Text #6

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.2430. Min Act: -0.0000

Data Index: 719971 (C4 (Web Text))

Max Activating Token Index: 910

Text #7

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.3831. Min Act: -0.0000

Data Index: 1228393 (C4 (Web Text))

Max Activating Token Index: 1011

Text #8

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.3551. Min Act: -0.0000

Data Index: 1123498 (C4 (Web Text))

Max Activating Token Index: 427

Text #9

Max Range: 6.5175. Min Range: -6.5175

Max Act: 3.9907. Min Act: -0.0000

Data Index: 1209456 (C4 (Web Text))

Max Activating Token Index: 118

Text #10

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.1024. Min Act: -0.0000

Data Index: 92545 (C4 (Web Text))

Max Activating Token Index: 255

Text #11

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.4082. Min Act: -0.0000

Data Index: 850406 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.0634. Min Act: -0.0000

Data Index: 478450 (C4 (Web Text))

Max Activating Token Index: 512

Text #13

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.1261. Min Act: -0.0000

Data Index: 1347932 (C4 (Web Text))

Max Activating Token Index: 580

Text #14

Max Range: 6.5175. Min Range: -6.5175

Max Act: 3.9543. Min Act: -0.0000

Data Index: 288578 (C4 (Web Text))

Max Activating Token Index: 250

Text #15

Max Range: 6.5175. Min Range: -6.5175

Max Act: 4.0565. Min Act: -0.0000

Data Index: 221966 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 6.5175. Min Range: -6.5175

Max Act: 3.8663. Min Act: -0.0000

Data Index: 22301 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 6.5175. Min Range: -6.5175

Max Act: 3.9635. Min Act: -0.0000

Data Index: 1108627 (C4 (Web Text))

Max Activating Token Index: 315

Text #18

Max Range: 6.5175. Min Range: -6.5175

Max Act: 3.9660. Min Act: -0.0000

Data Index: 435677 (C4 (Web Text))

Max Activating Token Index: 834

Text #19

Max Range: 6.5175. Min Range: -6.5175

Max Act: 3.7845. Min Act: -0.0000

Data Index: 618183 (C4 (Web Text))

Max Activating Token Index: 172