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

Dataset: The Pile

Neuron 4372 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: 0.4126. Min Range: -0.4126

Max Act: 0.4126. Min Act: -0.0000

Data Index: 579424 (The Pile)

Max Activating Token Index: 566

Text #1

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.3631. Min Act: -0.0000

Data Index: 489381 (The Pile)

Max Activating Token Index: 997

Text #2

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2989. Min Act: -0.0000

Data Index: 1722936 (The Pile)

Max Activating Token Index: 822

Text #3

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.3345. Min Act: -0.0000

Data Index: 455977 (The Pile)

Max Activating Token Index: 740

Text #4

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2983. Min Act: -0.0000

Data Index: 1605254 (The Pile)

Max Activating Token Index: 312

Text #5

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.3362. Min Act: -0.0000

Data Index: 964106 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.3064. Min Act: -0.0000

Data Index: 200610 (The Pile)

Max Activating Token Index: 511

Text #7

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2886. Min Act: -0.0000

Data Index: 856128 (The Pile)

Max Activating Token Index: 90

Text #8

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1973210 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2678. Min Act: -0.0000

Data Index: 318564 (The Pile)

Max Activating Token Index: 94

Text #10

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2755. Min Act: -0.0000

Data Index: 1070996 (The Pile)

Max Activating Token Index: 897

Text #11

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2553. Min Act: -0.0000

Data Index: 845087 (The Pile)

Max Activating Token Index: 45

Text #12

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2670. Min Act: -0.0000

Data Index: 659183 (The Pile)

Max Activating Token Index: 737

Text #13

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2741. Min Act: -0.0000

Data Index: 1099824 (The Pile)

Max Activating Token Index: 891

Text #14

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2709. Min Act: -0.0000

Data Index: 1318966 (The Pile)

Max Activating Token Index: 578

Text #15

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2725. Min Act: -0.0000

Data Index: 1655191 (The Pile)

Max Activating Token Index: 228

Text #16

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2611. Min Act: -0.0000

Data Index: 889055 (The Pile)

Max Activating Token Index: 870

Text #17

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2597. Min Act: -0.0000

Data Index: 1156717 (The Pile)

Max Activating Token Index: 427

Text #18

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2534. Min Act: -0.0000

Data Index: 483892 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 0.4126. Min Range: -0.4126

Max Act: 0.2533. Min Act: -0.0000

Data Index: 377097 (The Pile)

Max Activating Token Index: 977