Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2568 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 4.8831. Min Range: -4.8831

Max Act: 4.8831. Min Act: -0.0000

Data Index: 534320 (C4 (Web Text))

Max Activating Token Index: 987

Text #1

Max Range: 4.8831. Min Range: -4.8831

Max Act: 4.2125. Min Act: -0.0000

Data Index: 535272 (C4 (Web Text))

Max Activating Token Index: 1020

Text #2

Max Range: 4.8831. Min Range: -4.8831

Max Act: 4.0948. Min Act: -0.0000

Data Index: 755264 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 4.8831. Min Range: -4.8831

Max Act: 4.0735. Min Act: -0.0000

Data Index: 1022437 (C4 (Web Text))

Max Activating Token Index: 458

Text #4

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.9914. Min Act: -0.0000

Data Index: 1330654 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 4.8831. Min Range: -4.8831

Max Act: 4.2802. Min Act: -0.0000

Data Index: 173138 (C4 (Web Text))

Max Activating Token Index: 146

Text #6

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.6974. Min Act: -0.0000

Data Index: 1082277 (C4 (Web Text))

Max Activating Token Index: 384

Text #7

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.6949. Min Act: -0.0000

Data Index: 1009615 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.5102. Min Act: -0.0000

Data Index: 850863 (C4 (Web Text))

Max Activating Token Index: 115

Text #9

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.6670. Min Act: -0.0000

Data Index: 573567 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.6825. Min Act: -0.0000

Data Index: 868334 (C4 (Web Text))

Max Activating Token Index: 262

Text #11

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.8108. Min Act: -0.0000

Data Index: 744932 (C4 (Web Text))

Max Activating Token Index: 200

Text #12

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.5987. Min Act: -0.0000

Data Index: 1108933 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.5622. Min Act: -0.0000

Data Index: 807765 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.3767. Min Act: -0.0000

Data Index: 558025 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.8896. Min Act: -0.0000

Data Index: 236655 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.2799. Min Act: -0.0000

Data Index: 1065459 (C4 (Web Text))

Max Activating Token Index: 925

Text #17

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.3683. Min Act: -0.0000

Data Index: 846262 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.1867. Min Act: -0.0000

Data Index: 368397 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 4.8831. Min Range: -4.8831

Max Act: 3.4503. Min Act: -0.0000

Data Index: 1012637 (C4 (Web Text))

Max Activating Token Index: 698