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

Dataset: The Pile

Neuron 1656 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: 0.9925. Min Range: -0.9925

Max Act: 0.9925. Min Act: -0.0000

Data Index: 1628387 (The Pile)

Max Activating Token Index: 891

Text #1

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.8162. Min Act: -0.0000

Data Index: 653953 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1059523 (The Pile)

Max Activating Token Index: 294

Text #3

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5932. Min Act: -0.0000

Data Index: 1175895 (The Pile)

Max Activating Token Index: 671

Text #4

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6280. Min Act: -0.0000

Data Index: 1729948 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1304894 (The Pile)

Max Activating Token Index: 927

Text #6

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5547. Min Act: -0.0000

Data Index: 891903 (The Pile)

Max Activating Token Index: 785

Text #7

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6199. Min Act: -0.0000

Data Index: 590757 (The Pile)

Max Activating Token Index: 894

Text #8

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5732. Min Act: -0.0000

Data Index: 1321069 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5816. Min Act: -0.0000

Data Index: 959192 (The Pile)

Max Activating Token Index: 642

Text #10

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5750. Min Act: -0.0000

Data Index: 1802072 (The Pile)

Max Activating Token Index: 521

Text #11

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.6078. Min Act: -0.0000

Data Index: 1205442 (The Pile)

Max Activating Token Index: 764

Text #12

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1872726 (The Pile)

Max Activating Token Index: 362

Text #13

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5571. Min Act: -0.0000

Data Index: 602593 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5559. Min Act: -0.0000

Data Index: 590015 (The Pile)

Max Activating Token Index: 208

Text #15

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5556. Min Act: -0.0000

Data Index: 1373188 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5286. Min Act: -0.0000

Data Index: 112633 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.5348. Min Act: -0.0001

Data Index: 504492 (The Pile)

Max Activating Token Index: 922

Text #18

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.4779. Min Act: -0.0000

Data Index: 237438 (The Pile)

Max Activating Token Index: 791

Text #19

Max Range: 0.9925. Min Range: -0.9925

Max Act: 0.4991. Min Act: -0.0001

Data Index: 708752 (The Pile)

Max Activating Token Index: 677