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

Dataset: The Pile

Neuron 1700 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: 0.7472. Min Range: -0.7472

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1763134 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6358. Min Act: -0.0000

Data Index: 1011505 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5949. Min Act: -0.0000

Data Index: 161442 (The Pile)

Max Activating Token Index: 812

Text #3

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5839. Min Act: -0.0000

Data Index: 289681 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6070. Min Act: -0.0000

Data Index: 430836 (The Pile)

Max Activating Token Index: 608

Text #5

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.6157. Min Act: -0.0000

Data Index: 293020 (The Pile)

Max Activating Token Index: 651

Text #6

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5746. Min Act: -0.0000

Data Index: 1592555 (The Pile)

Max Activating Token Index: 332

Text #7

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5405. Min Act: -0.0000

Data Index: 1843243 (The Pile)

Max Activating Token Index: 706

Text #8

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5274. Min Act: -0.0000

Data Index: 393711 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5930. Min Act: -0.0000

Data Index: 611798 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1526813 (The Pile)

Max Activating Token Index: 139

Text #11

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4977. Min Act: -0.0000

Data Index: 453374 (The Pile)

Max Activating Token Index: 881

Text #12

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5102. Min Act: -0.0000

Data Index: 421313 (The Pile)

Max Activating Token Index: 597

Text #13

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1527264 (The Pile)

Max Activating Token Index: 970

Text #14

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5198. Min Act: -0.0000

Data Index: 288228 (The Pile)

Max Activating Token Index: 401

Text #15

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1712505 (The Pile)

Max Activating Token Index: 375

Text #16

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5469. Min Act: -0.0000

Data Index: 1593221 (The Pile)

Max Activating Token Index: 537

Text #17

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5222. Min Act: -0.0000

Data Index: 438852 (The Pile)

Max Activating Token Index: 838

Text #18

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.5206. Min Act: -0.0000

Data Index: 391196 (The Pile)

Max Activating Token Index: 580

Text #19

Max Range: 0.7472. Min Range: -0.7472

Max Act: 0.4382. Min Act: -0.0000

Data Index: 110511 (The Pile)

Max Activating Token Index: 622