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

Dataset: The Pile

Neuron 4671 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.3704. Min Act: -0.0000

Data Index: 911124 (The Pile)

Max Activating Token Index: 373

Text #1

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.3078. Min Act: -0.0000

Data Index: 1838426 (The Pile)

Max Activating Token Index: 79

Text #2

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9781. Min Act: -0.0000

Data Index: 608246 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.0268. Min Act: -0.0000

Data Index: 1688245 (The Pile)

Max Activating Token Index: 446

Text #4

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.0598. Min Act: -0.0000

Data Index: 1078406 (The Pile)

Max Activating Token Index: 173

Text #5

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.0287. Min Act: -0.0000

Data Index: 632614 (The Pile)

Max Activating Token Index: 6

Text #6

Max Range: 1.3704. Min Range: -1.3704

Max Act: 1.0044. Min Act: -0.0000

Data Index: 263847 (The Pile)

Max Activating Token Index: 350

Text #7

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9755. Min Act: -0.0000

Data Index: 311389 (The Pile)

Max Activating Token Index: 755

Text #8

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9842. Min Act: -0.0000

Data Index: 840037 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9394. Min Act: -0.0000

Data Index: 187450 (The Pile)

Max Activating Token Index: 188

Text #10

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9320. Min Act: -0.0000

Data Index: 1595021 (The Pile)

Max Activating Token Index: 530

Text #11

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9208. Min Act: -0.0000

Data Index: 182416 (The Pile)

Max Activating Token Index: 306

Text #12

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8504. Min Act: -0.0000

Data Index: 352071 (The Pile)

Max Activating Token Index: 909

Text #13

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8844. Min Act: -0.0000

Data Index: 803119 (The Pile)

Max Activating Token Index: 685

Text #14

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.9616. Min Act: -0.0000

Data Index: 947357 (The Pile)

Max Activating Token Index: 569

Text #15

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1746929 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8582. Min Act: -0.0000

Data Index: 1779664 (The Pile)

Max Activating Token Index: 672

Text #17

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8777. Min Act: -0.0000

Data Index: 396808 (The Pile)

Max Activating Token Index: 814

Text #18

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8553. Min Act: -0.0000

Data Index: 878986 (The Pile)

Max Activating Token Index: 355

Text #19

Max Range: 1.3704. Min Range: -1.3704

Max Act: 0.8970. Min Act: -0.0000

Data Index: 417747 (The Pile)

Max Activating Token Index: 187