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

Dataset: The Pile

Neuron 4722 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: 0.5466. Min Range: -0.5466

Max Act: 0.5335. Min Act: -0.0000

Data Index: 1483760 (The Pile)

Max Activating Token Index: 47

Text #1

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.5466. Min Act: -0.0000

Data Index: 957341 (The Pile)

Max Activating Token Index: 138

Text #2

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.5287. Min Act: -0.0000

Data Index: 1903391 (The Pile)

Max Activating Token Index: 172

Text #3

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4999. Min Act: -0.0000

Data Index: 1031744 (The Pile)

Max Activating Token Index: 675

Text #4

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4910. Min Act: -0.0000

Data Index: 286555 (The Pile)

Max Activating Token Index: 404

Text #5

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4524. Min Act: -0.0000

Data Index: 1595687 (The Pile)

Max Activating Token Index: 950

Text #6

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4966. Min Act: -0.0000

Data Index: 751644 (The Pile)

Max Activating Token Index: 518

Text #7

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4924. Min Act: -0.0000

Data Index: 884986 (The Pile)

Max Activating Token Index: 672

Text #8

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1382712 (The Pile)

Max Activating Token Index: 166

Text #9

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4680. Min Act: -0.0000

Data Index: 786524 (The Pile)

Max Activating Token Index: 474

Text #10

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4766. Min Act: -0.0000

Data Index: 355799 (The Pile)

Max Activating Token Index: 20

Text #11

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1377347 (The Pile)

Max Activating Token Index: 119

Text #12

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4442. Min Act: -0.0000

Data Index: 894921 (The Pile)

Max Activating Token Index: 60

Text #13

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4563. Min Act: -0.0000

Data Index: 64696 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1981629 (The Pile)

Max Activating Token Index: 774

Text #15

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4281. Min Act: -0.0000

Data Index: 974009 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4486. Min Act: -0.0000

Data Index: 385385 (The Pile)

Max Activating Token Index: 1014

Text #17

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4466. Min Act: -0.0000

Data Index: 1510877 (The Pile)

Max Activating Token Index: 676

Text #18

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.4323. Min Act: -0.0000

Data Index: 770845 (The Pile)

Max Activating Token Index: 247

Text #19

Max Range: 0.5466. Min Range: -0.5466

Max Act: 0.3922. Min Act: -0.0001

Data Index: 310010 (The Pile)

Max Activating Token Index: 968