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

Dataset: The Pile

Neuron 900 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.9425. Min Act: -0.0000

Data Index: 855226 (The Pile)

Max Activating Token Index: 1004

Text #1

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.9053. Min Act: 0.0000

Data Index: 912415 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8014. Min Act: -0.0000

Data Index: 1838148 (The Pile)

Max Activating Token Index: 942

Text #3

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7999. Min Act: -0.0000

Data Index: 495604 (The Pile)

Max Activating Token Index: 786

Text #4

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7743. Min Act: -0.0000

Data Index: 150633 (The Pile)

Max Activating Token Index: 49

Text #5

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8012. Min Act: -0.0000

Data Index: 1154658 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7051. Min Act: -0.0000

Data Index: 565867 (The Pile)

Max Activating Token Index: 368

Text #7

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8165. Min Act: -0.0000

Data Index: 1882933 (The Pile)

Max Activating Token Index: 1003

Text #8

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7383. Min Act: -0.0000

Data Index: 521779 (The Pile)

Max Activating Token Index: 51

Text #9

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8760. Min Act: -0.0000

Data Index: 1271177 (The Pile)

Max Activating Token Index: 485

Text #10

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.8030. Min Act: -0.0000

Data Index: 315267 (The Pile)

Max Activating Token Index: 919

Text #11

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7519. Min Act: -0.0000

Data Index: 840749 (The Pile)

Max Activating Token Index: 927

Text #12

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7805. Min Act: -0.0000

Data Index: 702433 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7050. Min Act: -0.0001

Data Index: 982907 (The Pile)

Max Activating Token Index: 897

Text #14

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6621. Min Act: -0.0000

Data Index: 1239412 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6385. Min Act: -0.0000

Data Index: 177349 (The Pile)

Max Activating Token Index: 660

Text #16

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7096. Min Act: -0.0000

Data Index: 1360790 (The Pile)

Max Activating Token Index: 701

Text #17

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.7118. Min Act: -0.0000

Data Index: 766611 (The Pile)

Max Activating Token Index: 463

Text #18

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6781. Min Act: -0.0000

Data Index: 1913693 (The Pile)

Max Activating Token Index: 559

Text #19

Max Range: 0.9425. Min Range: -0.9425

Max Act: 0.6676. Min Act: -0.0000

Data Index: 244299 (The Pile)

Max Activating Token Index: 1009