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

Dataset: The Pile

Neuron 4543 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: 0.5594. Min Range: -0.5594

Max Act: 0.5594. Min Act: -0.0000

Data Index: 1154657 (The Pile)

Max Activating Token Index: 748

Text #1

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1564302 (The Pile)

Max Activating Token Index: 724

Text #2

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5235. Min Act: -0.0000

Data Index: 1368464 (The Pile)

Max Activating Token Index: 1021

Text #3

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.5032. Min Act: -0.0000

Data Index: 39133 (The Pile)

Max Activating Token Index: 803

Text #4

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4885. Min Act: -0.0000

Data Index: 1543085 (The Pile)

Max Activating Token Index: 658

Text #5

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4829. Min Act: -0.0000

Data Index: 93171 (The Pile)

Max Activating Token Index: 653

Text #6

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4738. Min Act: -0.0000

Data Index: 496150 (The Pile)

Max Activating Token Index: 797

Text #7

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4547. Min Act: -0.0000

Data Index: 1847785 (The Pile)

Max Activating Token Index: 732

Text #8

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4463. Min Act: -0.0000

Data Index: 756716 (The Pile)

Max Activating Token Index: 997

Text #9

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4555. Min Act: -0.0000

Data Index: 1382947 (The Pile)

Max Activating Token Index: 966

Text #10

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4470. Min Act: -0.0000

Data Index: 413158 (The Pile)

Max Activating Token Index: 298

Text #11

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4693. Min Act: -0.0000

Data Index: 921956 (The Pile)

Max Activating Token Index: 917

Text #12

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4522. Min Act: -0.0000

Data Index: 1028643 (The Pile)

Max Activating Token Index: 720

Text #13

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4542. Min Act: -0.0000

Data Index: 1118298 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4486. Min Act: -0.0000

Data Index: 83494 (The Pile)

Max Activating Token Index: 1019

Text #15

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4513. Min Act: -0.0000

Data Index: 1565657 (The Pile)

Max Activating Token Index: 910

Text #16

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4402. Min Act: -0.0000

Data Index: 1427935 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4518. Min Act: -0.0000

Data Index: 1862785 (The Pile)

Max Activating Token Index: 616

Text #18

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4422. Min Act: -0.0000

Data Index: 270691 (The Pile)

Max Activating Token Index: 178

Text #19

Max Range: 0.5594. Min Range: -0.5594

Max Act: 0.4398. Min Act: -0.0000

Data Index: 1740585 (The Pile)

Max Activating Token Index: 687