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

Dataset: The Pile

Neuron 2713 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.9481. Min Act: -0.0000

Data Index: 1917954 (The Pile)

Max Activating Token Index: 653

Text #1

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.9279. Min Act: -0.0000

Data Index: 130652 (The Pile)

Max Activating Token Index: 828

Text #2

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.8785. Min Act: -0.0000

Data Index: 800753 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.7197. Min Act: -0.0000

Data Index: 1340169 (The Pile)

Max Activating Token Index: 530

Text #4

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.8095. Min Act: -0.0000

Data Index: 165957 (The Pile)

Max Activating Token Index: 341

Text #5

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.8363. Min Act: -0.0000

Data Index: 350150 (The Pile)

Max Activating Token Index: 800

Text #6

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.5437. Min Act: -0.0000

Data Index: 1562277 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.5290. Min Act: -0.0000

Data Index: 1273029 (The Pile)

Max Activating Token Index: 871

Text #8

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.8122. Min Act: -0.0000

Data Index: 553059 (The Pile)

Max Activating Token Index: 862

Text #9

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.5041. Min Act: -0.0000

Data Index: 825928 (The Pile)

Max Activating Token Index: 882

Text #10

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.6223. Min Act: -0.0000

Data Index: 343077 (The Pile)

Max Activating Token Index: 465

Text #11

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.5271. Min Act: -0.0000

Data Index: 363207 (The Pile)

Max Activating Token Index: 540

Text #12

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.5154. Min Act: -0.0000

Data Index: 1801194 (The Pile)

Max Activating Token Index: 373

Text #13

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.5086. Min Act: -0.0000

Data Index: 832393 (The Pile)

Max Activating Token Index: 770

Text #14

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.3873. Min Act: -0.0000

Data Index: 1546182 (The Pile)

Max Activating Token Index: 443

Text #15

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.3893. Min Act: -0.0000

Data Index: 243320 (The Pile)

Max Activating Token Index: 30

Text #16

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.4395. Min Act: -0.0000

Data Index: 923413 (The Pile)

Max Activating Token Index: 123

Text #17

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.3520. Min Act: -0.0000

Data Index: 1361810 (The Pile)

Max Activating Token Index: 737

Text #18

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.5061. Min Act: -0.0000

Data Index: 792701 (The Pile)

Max Activating Token Index: 523

Text #19

Max Range: 1.9481. Min Range: -1.9481

Max Act: 1.3190. Min Act: -0.0000

Data Index: 43399 (The Pile)

Max Activating Token Index: 963