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

Dataset: The Pile

Neuron 1830 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5963. Min Act: -0.0000

Data Index: 668476 (The Pile)

Max Activating Token Index: 402

Text #1

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5714. Min Act: -0.0000

Data Index: 793715 (The Pile)

Max Activating Token Index: 974

Text #2

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5573. Min Act: -0.0000

Data Index: 14515 (The Pile)

Max Activating Token Index: 828

Text #3

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5463. Min Act: -0.0000

Data Index: 919832 (The Pile)

Max Activating Token Index: 505

Text #4

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5435. Min Act: -0.0000

Data Index: 1652693 (The Pile)

Max Activating Token Index: 203

Text #5

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1752183 (The Pile)

Max Activating Token Index: 112

Text #6

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5731. Min Act: -0.0000

Data Index: 621893 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5374. Min Act: -0.0000

Data Index: 1050491 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4883. Min Act: -0.0000

Data Index: 185813 (The Pile)

Max Activating Token Index: 91

Text #9

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5472. Min Act: -0.0000

Data Index: 1775016 (The Pile)

Max Activating Token Index: 201

Text #10

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5125. Min Act: -0.0000

Data Index: 1564409 (The Pile)

Max Activating Token Index: 629

Text #11

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5276. Min Act: -0.0001

Data Index: 246975 (The Pile)

Max Activating Token Index: 217

Text #12

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4543. Min Act: -0.0000

Data Index: 528963 (The Pile)

Max Activating Token Index: 201

Text #13

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5393. Min Act: -0.0000

Data Index: 1419739 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4689. Min Act: -0.0000

Data Index: 1526080 (The Pile)

Max Activating Token Index: 874

Text #15

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.5624. Min Act: -0.0000

Data Index: 246622 (The Pile)

Max Activating Token Index: 764

Text #16

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4949. Min Act: -0.0000

Data Index: 1225928 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4911. Min Act: -0.0000

Data Index: 1897076 (The Pile)

Max Activating Token Index: 125

Text #18

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4890. Min Act: -0.0000

Data Index: 1935395 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.5963. Min Range: -0.5963

Max Act: 0.4659. Min Act: -0.0000

Data Index: 1249726 (The Pile)

Max Activating Token Index: 395