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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1769 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5501. Min Act: -0.0000

Data Index: 338027 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5132. Min Act: -0.0000

Data Index: 52314 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5196. Min Act: -0.0000

Data Index: 459681 (C4 (Web Text))

Max Activating Token Index: 597

Text #3

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.5017. Min Act: -0.0000

Data Index: 1004598 (C4 (Web Text))

Max Activating Token Index: 220

Text #4

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4742. Min Act: -0.0000

Data Index: 685316 (C4 (Web Text))

Max Activating Token Index: 467

Text #5

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4458. Min Act: -0.0000

Data Index: 1199387 (C4 (Web Text))

Max Activating Token Index: 603

Text #6

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4697. Min Act: -0.0000

Data Index: 750931 (C4 (Web Text))

Max Activating Token Index: 992

Text #7

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1132429 (C4 (Web Text))

Max Activating Token Index: 806

Text #8

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4335. Min Act: -0.0000

Data Index: 765787 (C4 (Web Text))

Max Activating Token Index: 802

Text #9

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4438. Min Act: -0.0000

Data Index: 468360 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4273. Min Act: -0.0000

Data Index: 1075496 (C4 (Web Text))

Max Activating Token Index: 903

Text #11

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4255. Min Act: -0.0000

Data Index: 569344 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1325729 (C4 (Web Text))

Max Activating Token Index: 330

Text #13

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4218. Min Act: -0.0000

Data Index: 95061 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4214. Min Act: -0.0000

Data Index: 1104888 (C4 (Web Text))

Max Activating Token Index: 853

Text #15

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.3997. Min Act: -0.0000

Data Index: 500855 (C4 (Web Text))

Max Activating Token Index: 255

Text #16

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4122. Min Act: -0.0000

Data Index: 290457 (C4 (Web Text))

Max Activating Token Index: 694

Text #17

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4124. Min Act: -0.0000

Data Index: 367710 (C4 (Web Text))

Max Activating Token Index: 493

Text #18

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4082. Min Act: -0.0000

Data Index: 1185626 (C4 (Web Text))

Max Activating Token Index: 144

Text #19

Max Range: 0.5501. Min Range: -0.5501

Max Act: 0.4096. Min Act: -0.0000

Data Index: 847870 (C4 (Web Text))

Max Activating Token Index: 254