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

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

Neuron 3787 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.5061. Min Act: -0.0001

Data Index: 377849 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4631. Min Act: -0.0001

Data Index: 1248722 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4719. Min Act: -0.0001

Data Index: 754348 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4702. Min Act: -0.0001

Data Index: 737823 (C4 (Web Text))

Max Activating Token Index: 60

Text #4

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4093. Min Act: -0.0001

Data Index: 1136886 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3937. Min Act: -0.0001

Data Index: 286086 (C4 (Web Text))

Max Activating Token Index: 870

Text #6

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4067. Min Act: -0.0001

Data Index: 1283946 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4273. Min Act: -0.0001

Data Index: 629565 (C4 (Web Text))

Max Activating Token Index: 658

Text #8

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4393. Min Act: -0.0001

Data Index: 258276 (C4 (Web Text))

Max Activating Token Index: 928

Text #9

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3800. Min Act: -0.0001

Data Index: 85877 (C4 (Web Text))

Max Activating Token Index: 498

Text #10

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3887. Min Act: -0.0001

Data Index: 77363 (C4 (Web Text))

Max Activating Token Index: 652

Text #11

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3921. Min Act: -0.0001

Data Index: 676388 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3806. Min Act: -0.0001

Data Index: 441248 (C4 (Web Text))

Max Activating Token Index: 316

Text #13

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3893. Min Act: -0.0001

Data Index: 1130324 (C4 (Web Text))

Max Activating Token Index: 1017

Text #14

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.4162. Min Act: -0.0001

Data Index: 774358 (C4 (Web Text))

Max Activating Token Index: 728

Text #15

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3418. Min Act: -0.0001

Data Index: 885100 (C4 (Web Text))

Max Activating Token Index: 650

Text #16

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3838. Min Act: -0.0001

Data Index: 356453 (C4 (Web Text))

Max Activating Token Index: 63

Text #17

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3842. Min Act: -0.0001

Data Index: 1088732 (C4 (Web Text))

Max Activating Token Index: 461

Text #18

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3824. Min Act: -0.0001

Data Index: 459740 (C4 (Web Text))

Max Activating Token Index: 480

Text #19

Max Range: 0.5061. Min Range: -0.5061

Max Act: 0.3541. Min Act: -0.0001

Data Index: 866225 (C4 (Web Text))

Max Activating Token Index: 712