Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3236 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.5077. Min Act: -0.0001

Data Index: 209715 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.5082. Min Act: -0.0001

Data Index: 680323 (C4 (Web Text))

Max Activating Token Index: 642

Text #2

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4799. Min Act: -0.0001

Data Index: 902114 (C4 (Web Text))

Max Activating Token Index: 279

Text #3

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4768. Min Act: -0.0001

Data Index: 926573 (C4 (Web Text))

Max Activating Token Index: 863

Text #4

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4362. Min Act: -0.0000

Data Index: 861582 (C4 (Web Text))

Max Activating Token Index: 603

Text #5

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4530. Min Act: -0.0000

Data Index: 1277456 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4440. Min Act: -0.0001

Data Index: 234385 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4486. Min Act: -0.0001

Data Index: 383754 (C4 (Web Text))

Max Activating Token Index: 690

Text #8

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4263. Min Act: -0.0000

Data Index: 1332535 (C4 (Web Text))

Max Activating Token Index: 106

Text #9

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4248. Min Act: -0.0001

Data Index: 80602 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4403. Min Act: -0.0001

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 941

Text #11

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4118. Min Act: -0.0001

Data Index: 540361 (C4 (Web Text))

Max Activating Token Index: 759

Text #12

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4221. Min Act: -0.0001

Data Index: 1141335 (C4 (Web Text))

Max Activating Token Index: 546

Text #13

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.3905. Min Act: -0.0001

Data Index: 336148 (C4 (Web Text))

Max Activating Token Index: 671

Text #14

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4058. Min Act: -0.0001

Data Index: 1335700 (C4 (Web Text))

Max Activating Token Index: 982

Text #15

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4232. Min Act: -0.0001

Data Index: 822647 (C4 (Web Text))

Max Activating Token Index: 877

Text #16

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4170. Min Act: -0.0001

Data Index: 739512 (C4 (Web Text))

Max Activating Token Index: 658

Text #17

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4261. Min Act: -0.0001

Data Index: 312693 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4257. Min Act: -0.0001

Data Index: 582377 (C4 (Web Text))

Max Activating Token Index: 587

Text #19

Max Range: 0.5082. Min Range: -0.5082

Max Act: 0.4113. Min Act: -0.0000

Data Index: 670704 (C4 (Web Text))

Max Activating Token Index: 407