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

Dataset: The Pile

Neuron 2689 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: 0.5607. Min Range: -0.5607

Max Act: 0.5607. Min Act: -0.0000

Data Index: 852662 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.5114. Min Act: -0.0000

Data Index: 393689 (The Pile)

Max Activating Token Index: 112

Text #2

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1204189 (The Pile)

Max Activating Token Index: 694

Text #3

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1842182 (The Pile)

Max Activating Token Index: 57

Text #4

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4493. Min Act: -0.0000

Data Index: 1007478 (The Pile)

Max Activating Token Index: 184

Text #5

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4192. Min Act: -0.0000

Data Index: 1722668 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3903. Min Act: -0.0000

Data Index: 656139 (The Pile)

Max Activating Token Index: 445

Text #7

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4013. Min Act: -0.0000

Data Index: 676883 (The Pile)

Max Activating Token Index: 163

Text #8

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3867. Min Act: -0.0000

Data Index: 1187358 (The Pile)

Max Activating Token Index: 225

Text #9

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.4052. Min Act: -0.0000

Data Index: 142543 (The Pile)

Max Activating Token Index: 78

Text #10

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3965. Min Act: -0.0000

Data Index: 1760200 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3670. Min Act: -0.0000

Data Index: 732224 (The Pile)

Max Activating Token Index: 214

Text #12

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3632. Min Act: -0.0000

Data Index: 422233 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3740. Min Act: -0.0000

Data Index: 154838 (The Pile)

Max Activating Token Index: 550

Text #14

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3857. Min Act: -0.0000

Data Index: 623300 (The Pile)

Max Activating Token Index: 231

Text #15

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3409. Min Act: -0.0001

Data Index: 622337 (The Pile)

Max Activating Token Index: 719

Text #16

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3777. Min Act: -0.0000

Data Index: 691303 (The Pile)

Max Activating Token Index: 928

Text #17

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3498. Min Act: -0.0000

Data Index: 1020915 (The Pile)

Max Activating Token Index: 596

Text #18

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3260. Min Act: -0.0000

Data Index: 427046 (The Pile)

Max Activating Token Index: 101

Text #19

Max Range: 0.5607. Min Range: -0.5607

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1575998 (The Pile)

Max Activating Token Index: 417