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

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

Neuron 5714 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0881. Min Act: -0.0001

Data Index: 117798 (C4 (Web Text))

Max Activating Token Index: 487

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0729. Min Act: -0.0001

Data Index: 419482 (C4 (Web Text))

Max Activating Token Index: 844

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0001

Data Index: 766047 (C4 (Web Text))

Max Activating Token Index: 807

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0788. Min Act: -0.0001

Data Index: 1206510 (C4 (Web Text))

Max Activating Token Index: 1017

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0795. Min Act: -0.0001

Data Index: 867100 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0777. Min Act: -0.0001

Data Index: 209971 (C4 (Web Text))

Max Activating Token Index: 594

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0727. Min Act: -0.0001

Data Index: 716152 (C4 (Web Text))

Max Activating Token Index: 714

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0769. Min Act: -0.0001

Data Index: 94778 (C4 (Web Text))

Max Activating Token Index: 137

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0833. Min Act: -0.0001

Data Index: 1096573 (C4 (Web Text))

Max Activating Token Index: 348

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0818. Min Act: -0.0001

Data Index: 526544 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0769. Min Act: -0.0001

Data Index: 126783 (C4 (Web Text))

Max Activating Token Index: 489

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0654. Min Act: -0.0001

Data Index: 1084077 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0809. Min Act: -0.0001

Data Index: 445862 (C4 (Web Text))

Max Activating Token Index: 313

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0675. Min Act: -0.0001

Data Index: 949291 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0681. Min Act: -0.0001

Data Index: 562522 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0646. Min Act: -0.0001

Data Index: 1243350 (C4 (Web Text))

Max Activating Token Index: 600

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0746. Min Act: -0.0001

Data Index: 593603 (C4 (Web Text))

Max Activating Token Index: 324

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0682. Min Act: -0.0001

Data Index: 1066276 (C4 (Web Text))

Max Activating Token Index: 256

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0652. Min Act: -0.0001

Data Index: 1107010 (C4 (Web Text))

Max Activating Token Index: 287

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0694. Min Act: -0.0001

Data Index: 382893 (C4 (Web Text))

Max Activating Token Index: 844