Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1783 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4372. Min Act: -0.0001

Data Index: 371963 (C4 (Web Text))

Max Activating Token Index: 578

Text #1

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4377. Min Act: -0.0001

Data Index: 1284417 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3809. Min Act: -0.0001

Data Index: 356015 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4482. Min Act: -0.0001

Data Index: 1164533 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4289. Min Act: -0.0001

Data Index: 1144978 (C4 (Web Text))

Max Activating Token Index: 573

Text #5

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4279. Min Act: -0.0001

Data Index: 64537 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4117. Min Act: -0.0001

Data Index: 883833 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4257. Min Act: -0.0001

Data Index: 1133659 (C4 (Web Text))

Max Activating Token Index: 590

Text #8

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4052. Min Act: -0.0001

Data Index: 78821 (C4 (Web Text))

Max Activating Token Index: 322

Text #9

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3953. Min Act: -0.0001

Data Index: 547955 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4079. Min Act: -0.0001

Data Index: 540458 (C4 (Web Text))

Max Activating Token Index: 793

Text #11

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4116. Min Act: -0.0001

Data Index: 347140 (C4 (Web Text))

Max Activating Token Index: 434

Text #12

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3918. Min Act: -0.0001

Data Index: 749630 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4017. Min Act: -0.0001

Data Index: 952967 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3972. Min Act: -0.0001

Data Index: 1115217 (C4 (Web Text))

Max Activating Token Index: 481

Text #15

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4212. Min Act: -0.0001

Data Index: 59522 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3830. Min Act: -0.0001

Data Index: 30496 (C4 (Web Text))

Max Activating Token Index: 826

Text #17

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.4318. Min Act: -0.0001

Data Index: 555195 (C4 (Web Text))

Max Activating Token Index: 779

Text #18

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3899. Min Act: -0.0001

Data Index: 1215419 (C4 (Web Text))

Max Activating Token Index: 876

Text #19

Max Range: 0.4482. Min Range: -0.4482

Max Act: 0.3880. Min Act: -0.0001

Data Index: 423135 (C4 (Web Text))

Max Activating Token Index: 851