Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2090 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7669. Min Act: -0.0000

Data Index: 223767 (The Pile)

Max Activating Token Index: 575

Text #1

Max Range: 3.0028. Min Range: -3.0028

Max Act: 3.0028. Min Act: -0.0000

Data Index: 484664 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.7128. Min Act: -0.0000

Data Index: 1016685 (The Pile)

Max Activating Token Index: 511

Text #3

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.4995. Min Act: -0.0000

Data Index: 1623810 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.2684. Min Act: -0.0000

Data Index: 344548 (The Pile)

Max Activating Token Index: 337

Text #5

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.1424. Min Act: -0.0000

Data Index: 937156 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0940. Min Act: -0.0000

Data Index: 627474 (The Pile)

Max Activating Token Index: 152

Text #7

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0597. Min Act: -0.0000

Data Index: 1713506 (The Pile)

Max Activating Token Index: 278

Text #8

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.2341. Min Act: -0.0000

Data Index: 544953 (The Pile)

Max Activating Token Index: 93

Text #9

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0158. Min Act: -0.0000

Data Index: 984185 (The Pile)

Max Activating Token Index: 373

Text #10

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0982. Min Act: -0.0000

Data Index: 897990 (The Pile)

Max Activating Token Index: 219

Text #11

Max Range: 3.0028. Min Range: -3.0028

Max Act: 1.9850. Min Act: -0.0000

Data Index: 136749 (The Pile)

Max Activating Token Index: 700

Text #12

Max Range: 3.0028. Min Range: -3.0028

Max Act: 1.9553. Min Act: -0.0000

Data Index: 1589022 (The Pile)

Max Activating Token Index: 685

Text #13

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0568. Min Act: -0.0000

Data Index: 1513985 (The Pile)

Max Activating Token Index: 279

Text #14

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0295. Min Act: -0.0000

Data Index: 725960 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 3.0028. Min Range: -3.0028

Max Act: 1.8258. Min Act: -0.0000

Data Index: 1352222 (The Pile)

Max Activating Token Index: 634

Text #16

Max Range: 3.0028. Min Range: -3.0028

Max Act: 2.0817. Min Act: -0.0000

Data Index: 1406450 (The Pile)

Max Activating Token Index: 823

Text #17

Max Range: 3.0028. Min Range: -3.0028

Max Act: 1.9887. Min Act: -0.0000

Data Index: 979944 (The Pile)

Max Activating Token Index: 1014

Text #18

Max Range: 3.0028. Min Range: -3.0028

Max Act: 1.9924. Min Act: -0.0000

Data Index: 677032 (The Pile)

Max Activating Token Index: 935

Text #19

Max Range: 3.0028. Min Range: -3.0028

Max Act: 1.7392. Min Act: -0.0000

Data Index: 617130 (The Pile)

Max Activating Token Index: 101