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

Dataset: The Pile

Neuron 2353 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: 0.5891. Min Range: -0.5891

Max Act: 0.5708. Min Act: -0.0001

Data Index: 1580120 (The Pile)

Max Activating Token Index: 486

Text #1

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4927. Min Act: -0.0000

Data Index: 1083614 (The Pile)

Max Activating Token Index: 146

Text #2

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5217. Min Act: -0.0000

Data Index: 1161378 (The Pile)

Max Activating Token Index: 380

Text #3

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4307. Min Act: -0.0000

Data Index: 91675 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5379. Min Act: -0.0000

Data Index: 1349328 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5891. Min Act: -0.0000

Data Index: 1622630 (The Pile)

Max Activating Token Index: 868

Text #6

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5172. Min Act: -0.0000

Data Index: 824335 (The Pile)

Max Activating Token Index: 545

Text #7

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4630. Min Act: -0.0000

Data Index: 178233 (The Pile)

Max Activating Token Index: 634

Text #8

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.5182. Min Act: -0.0000

Data Index: 3966 (The Pile)

Max Activating Token Index: 14

Text #9

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4796. Min Act: -0.0000

Data Index: 366092 (The Pile)

Max Activating Token Index: 493

Text #10

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4395. Min Act: -0.0000

Data Index: 862042 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4935. Min Act: -0.0000

Data Index: 497363 (The Pile)

Max Activating Token Index: 30

Text #12

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4673. Min Act: -0.0000

Data Index: 1557225 (The Pile)

Max Activating Token Index: 884

Text #13

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1939740 (The Pile)

Max Activating Token Index: 939

Text #14

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1836181 (The Pile)

Max Activating Token Index: 503

Text #15

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4477. Min Act: -0.0000

Data Index: 73329 (The Pile)

Max Activating Token Index: 493

Text #16

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4671. Min Act: -0.0000

Data Index: 1641099 (The Pile)

Max Activating Token Index: 622

Text #17

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4328. Min Act: -0.0000

Data Index: 435945 (The Pile)

Max Activating Token Index: 301

Text #18

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4722. Min Act: -0.0000

Data Index: 639159 (The Pile)

Max Activating Token Index: 595

Text #19

Max Range: 0.5891. Min Range: -0.5891

Max Act: 0.4242. Min Act: -0.0000

Data Index: 982352 (The Pile)

Max Activating Token Index: 560