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

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

Neuron 3728 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.6112. Min Act: -0.0000

Data Index: 822320 (C4 (Web Text))

Max Activating Token Index: 847

Text #1

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.5716. Min Act: -0.0000

Data Index: 672543 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.5658. Min Act: -0.0000

Data Index: 327937 (C4 (Web Text))

Max Activating Token Index: 1012

Text #3

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4897. Min Act: -0.0000

Data Index: 737594 (C4 (Web Text))

Max Activating Token Index: 474

Text #4

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1075888 (C4 (Web Text))

Max Activating Token Index: 499

Text #5

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.5289. Min Act: -0.0000

Data Index: 483126 (C4 (Web Text))

Max Activating Token Index: 1018

Text #6

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4732. Min Act: -0.0000

Data Index: 142878 (C4 (Web Text))

Max Activating Token Index: 826

Text #7

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4791. Min Act: 0.0000

Data Index: 8644 (C4 (Web Text))

Max Activating Token Index: 728

Text #8

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4920. Min Act: -0.0000

Data Index: 1302409 (C4 (Web Text))

Max Activating Token Index: 800

Text #9

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4608. Min Act: -0.0000

Data Index: 188322 (C4 (Web Text))

Max Activating Token Index: 80

Text #10

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4628. Min Act: 0.0001

Data Index: 977872 (C4 (Web Text))

Max Activating Token Index: 896

Text #11

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4734. Min Act: -0.0000

Data Index: 1296134 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4782. Min Act: 0.0000

Data Index: 1328968 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4624. Min Act: -0.0000

Data Index: 838791 (C4 (Web Text))

Max Activating Token Index: 631

Text #14

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4591. Min Act: -0.0000

Data Index: 576017 (C4 (Web Text))

Max Activating Token Index: 863

Text #15

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4591. Min Act: -0.0000

Data Index: 1108604 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4273. Min Act: -0.0000

Data Index: 687770 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4386. Min Act: -0.0000

Data Index: 847470 (C4 (Web Text))

Max Activating Token Index: 190

Text #18

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4513. Min Act: 0.0000

Data Index: 212416 (C4 (Web Text))

Max Activating Token Index: 339

Text #19

Max Range: 0.6112. Min Range: -0.6112

Max Act: 0.4145. Min Act: -0.0000

Data Index: 755003 (C4 (Web Text))

Max Activating Token Index: 487