Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4531 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 8.7339. Min Range: -8.7339

Max Act: 8.7331. Min Act: -0.0000

Data Index: 1566935 (The Pile)

Max Activating Token Index: 139

Text #1

Max Range: 8.7339. Min Range: -8.7339

Max Act: 8.7339. Min Act: -0.0000

Data Index: 1718775 (The Pile)

Max Activating Token Index: 931

Text #2

Max Range: 8.7339. Min Range: -8.7339

Max Act: 7.0734. Min Act: -0.0000

Data Index: 1105491 (The Pile)

Max Activating Token Index: 139

Text #3

Max Range: 8.7339. Min Range: -8.7339

Max Act: 7.0261. Min Act: -0.0000

Data Index: 260775 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 8.7339. Min Range: -8.7339

Max Act: 7.1865. Min Act: -0.0000

Data Index: 979988 (The Pile)

Max Activating Token Index: 262

Text #5

Max Range: 8.7339. Min Range: -8.7339

Max Act: 7.0378. Min Act: -0.0000

Data Index: 1215087 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.4024. Min Act: -0.0000

Data Index: 923405 (The Pile)

Max Activating Token Index: 722

Text #7

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.4730. Min Act: -0.0000

Data Index: 1300566 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.5661. Min Act: -0.0000

Data Index: 1189184 (The Pile)

Max Activating Token Index: 121

Text #9

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.6095. Min Act: -0.0000

Data Index: 911339 (The Pile)

Max Activating Token Index: 854

Text #10

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.4412. Min Act: -0.0000

Data Index: 1878953 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.2271. Min Act: -0.0000

Data Index: 1165510 (The Pile)

Max Activating Token Index: 816

Text #12

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.1702. Min Act: -0.0000

Data Index: 280113 (The Pile)

Max Activating Token Index: 355

Text #13

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.4977. Min Act: -0.0000

Data Index: 826478 (The Pile)

Max Activating Token Index: 955

Text #14

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.3014. Min Act: -0.0000

Data Index: 42034 (The Pile)

Max Activating Token Index: 430

Text #15

Max Range: 8.7339. Min Range: -8.7339

Max Act: 5.5187. Min Act: -0.0000

Data Index: 824826 (The Pile)

Max Activating Token Index: 628

Text #16

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.5006. Min Act: -0.0000

Data Index: 908322 (The Pile)

Max Activating Token Index: 57

Text #17

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.3285. Min Act: -0.0000

Data Index: 187127 (The Pile)

Max Activating Token Index: 311

Text #18

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.7741. Min Act: -0.0000

Data Index: 986636 (The Pile)

Max Activating Token Index: 1021

Text #19

Max Range: 8.7339. Min Range: -8.7339

Max Act: 6.5413. Min Act: -0.0000

Data Index: 605017 (The Pile)

Max Activating Token Index: 715