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

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

Neuron 1072 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.7661. Min Act: -0.0000

Data Index: 660291 (C4 (Web Text))

Max Activating Token Index: 204

Text #1

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.7273. Min Act: -0.0000

Data Index: 969904 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.7445. Min Act: -0.0001

Data Index: 694177 (C4 (Web Text))

Max Activating Token Index: 1009

Text #3

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6814. Min Act: -0.0000

Data Index: 787965 (C4 (Web Text))

Max Activating Token Index: 581

Text #4

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6815. Min Act: -0.0001

Data Index: 937205 (C4 (Web Text))

Max Activating Token Index: 920

Text #5

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6564. Min Act: -0.0000

Data Index: 617937 (C4 (Web Text))

Max Activating Token Index: 775

Text #6

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6486. Min Act: -0.0000

Data Index: 619525 (C4 (Web Text))

Max Activating Token Index: 660

Text #7

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6419. Min Act: -0.0001

Data Index: 803975 (C4 (Web Text))

Max Activating Token Index: 496

Text #8

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.6269. Min Act: -0.0001

Data Index: 222736 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5992. Min Act: -0.0001

Data Index: 344913 (C4 (Web Text))

Max Activating Token Index: 1020

Text #10

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5492. Min Act: -0.0000

Data Index: 406582 (C4 (Web Text))

Max Activating Token Index: 990

Text #11

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5456. Min Act: -0.0000

Data Index: 1227566 (C4 (Web Text))

Max Activating Token Index: 180

Text #12

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5670. Min Act: -0.0001

Data Index: 1252219 (C4 (Web Text))

Max Activating Token Index: 218

Text #13

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5516. Min Act: -0.0001

Data Index: 155578 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5581. Min Act: -0.0000

Data Index: 818803 (C4 (Web Text))

Max Activating Token Index: 824

Text #15

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5403. Min Act: -0.0000

Data Index: 521486 (C4 (Web Text))

Max Activating Token Index: 434

Text #16

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5584. Min Act: -0.0000

Data Index: 278464 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5258. Min Act: -0.0000

Data Index: 421823 (C4 (Web Text))

Max Activating Token Index: 913

Text #18

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.4956. Min Act: -0.0000

Data Index: 176464 (C4 (Web Text))

Max Activating Token Index: 222

Text #19

Max Range: 0.7661. Min Range: -0.7661

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1178941 (C4 (Web Text))

Max Activating Token Index: 654