Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1783 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.7113. Min Act: -0.0000

Data Index: 1603150 (The Pile)

Max Activating Token Index: 727

Text #1

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.6232. Min Act: -0.0000

Data Index: 1829236 (The Pile)

Max Activating Token Index: 544

Text #2

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.2538. Min Act: -0.0000

Data Index: 1229450 (The Pile)

Max Activating Token Index: 127

Text #3

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.3211. Min Act: -0.0000

Data Index: 1456787 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.2816. Min Act: -0.0000

Data Index: 931766 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.9753. Min Act: -0.0000

Data Index: 1535010 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.3647. Min Act: -0.0000

Data Index: 528181 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.8059. Min Act: -0.0000

Data Index: 983743 (The Pile)

Max Activating Token Index: 976

Text #8

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.0259. Min Act: -0.0000

Data Index: 679831 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.0982. Min Act: -0.0000

Data Index: 362329 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.8238. Min Act: -0.0000

Data Index: 894334 (The Pile)

Max Activating Token Index: 488

Text #11

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.0641. Min Act: -0.0000

Data Index: 395330 (The Pile)

Max Activating Token Index: 913

Text #12

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.7731. Min Act: -0.0000

Data Index: 1967814 (The Pile)

Max Activating Token Index: 282

Text #13

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.8748. Min Act: -0.0000

Data Index: 165514 (The Pile)

Max Activating Token Index: 797

Text #14

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.0214. Min Act: -0.0000

Data Index: 846301 (The Pile)

Max Activating Token Index: 611

Text #15

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.9896. Min Act: -0.0000

Data Index: 1340999 (The Pile)

Max Activating Token Index: 523

Text #16

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.8266. Min Act: -0.0000

Data Index: 696774 (The Pile)

Max Activating Token Index: 17

Text #17

Max Range: 3.7113. Min Range: -3.7113

Max Act: 3.0441. Min Act: -0.0000

Data Index: 416394 (The Pile)

Max Activating Token Index: 373

Text #18

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.7817. Min Act: -0.0000

Data Index: 1519161 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 3.7113. Min Range: -3.7113

Max Act: 2.7696. Min Act: -0.0000

Data Index: 1810416 (The Pile)

Max Activating Token Index: 92