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

Dataset: The Pile

Neuron 2075 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.7410. Min Act: -0.0000

Data Index: 1350661 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.4878. Min Act: -0.0000

Data Index: 927607 (The Pile)

Max Activating Token Index: 105

Text #2

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.3363. Min Act: -0.0000

Data Index: 15864 (The Pile)

Max Activating Token Index: 593

Text #3

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.2039. Min Act: -0.0000

Data Index: 161346 (The Pile)

Max Activating Token Index: 165

Text #4

Max Range: 1.7410. Min Range: -1.7410

Max Act: 1.0139. Min Act: -0.0000

Data Index: 985809 (The Pile)

Max Activating Token Index: 415

Text #5

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.9750. Min Act: -0.0000

Data Index: 1446278 (The Pile)

Max Activating Token Index: 421

Text #6

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.9382. Min Act: -0.0000

Data Index: 1455326 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.9576. Min Act: -0.0000

Data Index: 1155472 (The Pile)

Max Activating Token Index: 283

Text #8

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.9947. Min Act: -0.0000

Data Index: 1996386 (The Pile)

Max Activating Token Index: 840

Text #9

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1823912 (The Pile)

Max Activating Token Index: 597

Text #10

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.9478. Min Act: -0.0000

Data Index: 136881 (The Pile)

Max Activating Token Index: 627

Text #11

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.8622. Min Act: -0.0000

Data Index: 1228558 (The Pile)

Max Activating Token Index: 390

Text #12

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.8712. Min Act: -0.0000

Data Index: 1537598 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.8280. Min Act: -0.0000

Data Index: 132915 (The Pile)

Max Activating Token Index: 722

Text #14

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.8415. Min Act: -0.0000

Data Index: 4483 (The Pile)

Max Activating Token Index: 633

Text #15

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.7820. Min Act: -0.0000

Data Index: 1849070 (The Pile)

Max Activating Token Index: 631

Text #16

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.8792. Min Act: -0.0000

Data Index: 24991 (The Pile)

Max Activating Token Index: 46

Text #17

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.8880. Min Act: -0.0000

Data Index: 907891 (The Pile)

Max Activating Token Index: 419

Text #18

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.8541. Min Act: -0.0000

Data Index: 686855 (The Pile)

Max Activating Token Index: 532

Text #19

Max Range: 1.7410. Min Range: -1.7410

Max Act: 0.7980. Min Act: -0.0000

Data Index: 1694607 (The Pile)

Max Activating Token Index: 692