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

Dataset: The Pile

Neuron 4072 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1074136 (The Pile)

Max Activating Token Index: 385

Text #1

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.5604. Min Act: -0.0000

Data Index: 112782 (The Pile)

Max Activating Token Index: 194

Text #2

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.5410. Min Act: -0.0000

Data Index: 645129 (The Pile)

Max Activating Token Index: 708

Text #3

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.5350. Min Act: -0.0000

Data Index: 747764 (The Pile)

Max Activating Token Index: 847

Text #4

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.5816. Min Act: -0.0000

Data Index: 91470 (The Pile)

Max Activating Token Index: 903

Text #5

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.6418. Min Act: -0.0000

Data Index: 116016 (The Pile)

Max Activating Token Index: 979

Text #6

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.5661. Min Act: -0.0000

Data Index: 1787150 (The Pile)

Max Activating Token Index: 570

Text #7

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.5510. Min Act: -0.0000

Data Index: 591891 (The Pile)

Max Activating Token Index: 421

Text #8

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4967. Min Act: -0.0000

Data Index: 933818 (The Pile)

Max Activating Token Index: 525

Text #9

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4779. Min Act: -0.0000

Data Index: 1288411 (The Pile)

Max Activating Token Index: 620

Text #10

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4875. Min Act: -0.0000

Data Index: 840399 (The Pile)

Max Activating Token Index: 334

Text #11

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4900. Min Act: -0.0000

Data Index: 1531999 (The Pile)

Max Activating Token Index: 570

Text #12

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4846. Min Act: -0.0000

Data Index: 1079450 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4374. Min Act: -0.0000

Data Index: 1794131 (The Pile)

Max Activating Token Index: 450

Text #14

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4666. Min Act: -0.0000

Data Index: 863424 (The Pile)

Max Activating Token Index: 522

Text #15

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.5069. Min Act: -0.0000

Data Index: 301411 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4274. Min Act: -0.0000

Data Index: 893247 (The Pile)

Max Activating Token Index: 687

Text #17

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4609. Min Act: -0.0000

Data Index: 1464214 (The Pile)

Max Activating Token Index: 824

Text #18

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4556. Min Act: -0.0000

Data Index: 423863 (The Pile)

Max Activating Token Index: 357

Text #19

Max Range: 0.9535. Min Range: -0.9535

Max Act: 0.4632. Min Act: -0.0000

Data Index: 933656 (The Pile)

Max Activating Token Index: 193