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

Dataset: The Pile

Neuron 1912 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5816. Min Range: -3.5816

Max Act: 3.5816. Min Act: -0.0000

Data Index: 1980317 (The Pile)

Max Activating Token Index: 694

Text #1

Max Range: 3.5816. Min Range: -3.5816

Max Act: 2.4862. Min Act: -0.0000

Data Index: 1404861 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 3.5816. Min Range: -3.5816

Max Act: 2.3508. Min Act: 0.0000

Data Index: 960975 (The Pile)

Max Activating Token Index: 692

Text #3

Max Range: 3.5816. Min Range: -3.5816

Max Act: 2.1879. Min Act: -0.0000

Data Index: 206568 (The Pile)

Max Activating Token Index: 799

Text #4

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.9686. Min Act: -0.0000

Data Index: 828400 (The Pile)

Max Activating Token Index: 933

Text #5

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.7039. Min Act: -0.0000

Data Index: 150045 (The Pile)

Max Activating Token Index: 179

Text #6

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.7687. Min Act: -0.0000

Data Index: 1320510 (The Pile)

Max Activating Token Index: 386

Text #7

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.7553. Min Act: 0.0001

Data Index: 272757 (The Pile)

Max Activating Token Index: 963

Text #8

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.7483. Min Act: -0.0000

Data Index: 264401 (The Pile)

Max Activating Token Index: 900

Text #9

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.6442. Min Act: -0.0000

Data Index: 456376 (The Pile)

Max Activating Token Index: 938

Text #10

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.6215. Min Act: -0.0000

Data Index: 710287 (The Pile)

Max Activating Token Index: 33

Text #11

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.5122. Min Act: -0.0000

Data Index: 1171490 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.5144. Min Act: -0.0000

Data Index: 1205712 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.4903. Min Act: -0.0000

Data Index: 1789066 (The Pile)

Max Activating Token Index: 691

Text #14

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.5649. Min Act: -0.0000

Data Index: 869520 (The Pile)

Max Activating Token Index: 131

Text #15

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.4295. Min Act: -0.0000

Data Index: 219898 (The Pile)

Max Activating Token Index: 514

Text #16

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.4603. Min Act: -0.0000

Data Index: 1542875 (The Pile)

Max Activating Token Index: 1008

Text #17

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.3773. Min Act: -0.0000

Data Index: 833064 (The Pile)

Max Activating Token Index: 778

Text #18

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.3494. Min Act: -0.0000

Data Index: 1514624 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 3.5816. Min Range: -3.5816

Max Act: 1.4407. Min Act: -0.0000

Data Index: 444325 (The Pile)

Max Activating Token Index: 869