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

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

Neuron 1733 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.9877. Min Act: -0.0001

Data Index: 1280724 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.8858. Min Act: -0.0001

Data Index: 1026576 (C4 (Web Text))

Max Activating Token Index: 990

Text #2

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7564. Min Act: -0.0001

Data Index: 992033 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7061. Min Act: -0.0001

Data Index: 329630 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7506. Min Act: -0.0001

Data Index: 1286609 (C4 (Web Text))

Max Activating Token Index: 132

Text #5

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7680. Min Act: -0.0001

Data Index: 132015 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7841. Min Act: -0.0001

Data Index: 484690 (C4 (Web Text))

Max Activating Token Index: 284

Text #7

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7755. Min Act: -0.0001

Data Index: 452210 (C4 (Web Text))

Max Activating Token Index: 1021

Text #8

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7032. Min Act: -0.0001

Data Index: 117993 (C4 (Web Text))

Max Activating Token Index: 307

Text #9

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.7124. Min Act: -0.0001

Data Index: 159323 (C4 (Web Text))

Max Activating Token Index: 917

Text #10

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6249. Min Act: -0.0001

Data Index: 1007482 (C4 (Web Text))

Max Activating Token Index: 803

Text #11

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6734. Min Act: -0.0001

Data Index: 533760 (C4 (Web Text))

Max Activating Token Index: 370

Text #12

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6504. Min Act: -0.0001

Data Index: 859657 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6309. Min Act: -0.0001

Data Index: 439783 (C4 (Web Text))

Max Activating Token Index: 512

Text #14

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5428. Min Act: -0.0001

Data Index: 920073 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5844. Min Act: -0.0001

Data Index: 116903 (C4 (Web Text))

Max Activating Token Index: 1006

Text #16

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6128. Min Act: -0.0001

Data Index: 448466 (C4 (Web Text))

Max Activating Token Index: 604

Text #17

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5773. Min Act: -0.0001

Data Index: 81094 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.6754. Min Act: -0.0001

Data Index: 782179 (C4 (Web Text))

Max Activating Token Index: 67

Text #19

Max Range: 0.9877. Min Range: -0.9877

Max Act: 0.5978. Min Act: -0.0001

Data Index: 260631 (C4 (Web Text))

Max Activating Token Index: 57