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

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

Neuron 3877 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7233. Min Act: -0.0001

Data Index: 357787 (C4 (Web Text))

Max Activating Token Index: 637

Text #1

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7427. Min Act: -0.0000

Data Index: 1347521 (C4 (Web Text))

Max Activating Token Index: 1008

Text #2

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6572. Min Act: -0.0000

Data Index: 62163 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7524. Min Act: -0.0001

Data Index: 251224 (C4 (Web Text))

Max Activating Token Index: 754

Text #4

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7618. Min Act: -0.0000

Data Index: 796317 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7195. Min Act: -0.0001

Data Index: 964884 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7136. Min Act: -0.0000

Data Index: 211924 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6858. Min Act: -0.0001

Data Index: 880438 (C4 (Web Text))

Max Activating Token Index: 832

Text #8

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6609. Min Act: -0.0000

Data Index: 21373 (C4 (Web Text))

Max Activating Token Index: 1021

Text #9

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7353. Min Act: -0.0000

Data Index: 699277 (C4 (Web Text))

Max Activating Token Index: 886

Text #10

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7123. Min Act: -0.0001

Data Index: 422206 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6837. Min Act: -0.0000

Data Index: 588533 (C4 (Web Text))

Max Activating Token Index: 260

Text #12

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6540. Min Act: -0.0001

Data Index: 637204 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6057. Min Act: -0.0001

Data Index: 546607 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7023. Min Act: -0.0001

Data Index: 649666 (C4 (Web Text))

Max Activating Token Index: 890

Text #15

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.7216. Min Act: -0.0001

Data Index: 181319 (C4 (Web Text))

Max Activating Token Index: 147

Text #16

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6824. Min Act: -0.0001

Data Index: 167208 (C4 (Web Text))

Max Activating Token Index: 156

Text #17

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6427. Min Act: -0.0001

Data Index: 1117869 (C4 (Web Text))

Max Activating Token Index: 395

Text #18

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6218. Min Act: -0.0001

Data Index: 263993 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.7618. Min Range: -0.7618

Max Act: 0.6626. Min Act: -0.0001

Data Index: 462983 (C4 (Web Text))

Max Activating Token Index: 1008