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

Dataset: The Pile

Neuron 4537 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: 4.1631. Min Range: -4.1631

Max Act: 4.1631. Min Act: -0.0000

Data Index: 1165412 (The Pile)

Max Activating Token Index: 746

Text #1

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.9458. Min Act: -0.0000

Data Index: 827955 (The Pile)

Max Activating Token Index: 920

Text #2

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.8897. Min Act: -0.0000

Data Index: 552708 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.6184. Min Act: -0.0000

Data Index: 1743432 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.3494. Min Act: -0.0000

Data Index: 1084756 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.4179. Min Act: -0.0000

Data Index: 1570937 (The Pile)

Max Activating Token Index: 677

Text #6

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.2551. Min Act: -0.0000

Data Index: 1460857 (The Pile)

Max Activating Token Index: 60

Text #7

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.5460. Min Act: -0.0000

Data Index: 1296920 (The Pile)

Max Activating Token Index: 809

Text #8

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.3648. Min Act: -0.0000

Data Index: 1308681 (The Pile)

Max Activating Token Index: 106

Text #9

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.4943. Min Act: -0.0000

Data Index: 1218109 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.1674. Min Act: -0.0000

Data Index: 1090120 (The Pile)

Max Activating Token Index: 121

Text #11

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.1734. Min Act: -0.0000

Data Index: 864682 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.2998. Min Act: -0.0000

Data Index: 700064 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.1385. Min Act: -0.0000

Data Index: 887158 (The Pile)

Max Activating Token Index: 702

Text #14

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.4430. Min Act: -0.0000

Data Index: 1674631 (The Pile)

Max Activating Token Index: 622

Text #15

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.2821. Min Act: -0.0000

Data Index: 1305721 (The Pile)

Max Activating Token Index: 614

Text #16

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.2909. Min Act: -0.0000

Data Index: 1021681 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.1335. Min Act: -0.0000

Data Index: 640563 (The Pile)

Max Activating Token Index: 800

Text #18

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.2139. Min Act: -0.0000

Data Index: 179599 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 4.1631. Min Range: -4.1631

Max Act: 3.2429. Min Act: -0.0000

Data Index: 87675 (The Pile)

Max Activating Token Index: 488