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

Dataset: The Pile

Neuron 2331 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6379. Min Act: -0.0000

Data Index: 444361 (The Pile)

Max Activating Token Index: 283

Text #1

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5530. Min Act: -0.0000

Data Index: 1598680 (The Pile)

Max Activating Token Index: 224

Text #2

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1916307 (The Pile)

Max Activating Token Index: 463

Text #3

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5627. Min Act: -0.0000

Data Index: 1876569 (The Pile)

Max Activating Token Index: 861

Text #4

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5586. Min Act: -0.0000

Data Index: 409998 (The Pile)

Max Activating Token Index: 734

Text #5

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5344. Min Act: -0.0001

Data Index: 1759629 (The Pile)

Max Activating Token Index: 145

Text #6

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5255. Min Act: -0.0001

Data Index: 1687949 (The Pile)

Max Activating Token Index: 327

Text #7

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5197. Min Act: -0.0000

Data Index: 1614341 (The Pile)

Max Activating Token Index: 93

Text #8

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5027. Min Act: -0.0001

Data Index: 1083890 (The Pile)

Max Activating Token Index: 50

Text #9

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5186. Min Act: -0.0000

Data Index: 758062 (The Pile)

Max Activating Token Index: 672

Text #10

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5042. Min Act: -0.0001

Data Index: 216714 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4852. Min Act: -0.0001

Data Index: 993681 (The Pile)

Max Activating Token Index: 618

Text #12

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4731. Min Act: -0.0000

Data Index: 172694 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4933. Min Act: -0.0000

Data Index: 1896237 (The Pile)

Max Activating Token Index: 266

Text #14

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4742. Min Act: -0.0001

Data Index: 1854059 (The Pile)

Max Activating Token Index: 519

Text #15

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4762. Min Act: -0.0001

Data Index: 670952 (The Pile)

Max Activating Token Index: 113

Text #16

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4576. Min Act: -0.0000

Data Index: 20853 (The Pile)

Max Activating Token Index: 633

Text #17

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5223. Min Act: -0.0000

Data Index: 475878 (The Pile)

Max Activating Token Index: 192

Text #18

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4822. Min Act: -0.0000

Data Index: 299940 (The Pile)

Max Activating Token Index: 799

Text #19

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4257. Min Act: -0.0000

Data Index: 1322078 (The Pile)

Max Activating Token Index: 920