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

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

Neuron 3359 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5973. Min Act: -0.0003

Data Index: 153948 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4567. Min Act: -0.0003

Data Index: 17824 (C4 (Web Text))

Max Activating Token Index: 883

Text #2

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5244. Min Act: -0.0003

Data Index: 293955 (C4 (Web Text))

Max Activating Token Index: 282

Text #3

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4955. Min Act: -0.0003

Data Index: 953895 (C4 (Web Text))

Max Activating Token Index: 1005

Text #4

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4884. Min Act: -0.0003

Data Index: 1075608 (C4 (Web Text))

Max Activating Token Index: 535

Text #5

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.5034. Min Act: -0.0003

Data Index: 711678 (C4 (Web Text))

Max Activating Token Index: 154

Text #6

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4836. Min Act: -0.0003

Data Index: 33407 (C4 (Web Text))

Max Activating Token Index: 771

Text #7

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4808. Min Act: -0.0003

Data Index: 337418 (C4 (Web Text))

Max Activating Token Index: 94

Text #8

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4911. Min Act: -0.0003

Data Index: 279768 (C4 (Web Text))

Max Activating Token Index: 447

Text #9

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4937. Min Act: -0.0003

Data Index: 85317 (C4 (Web Text))

Max Activating Token Index: 820

Text #10

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4604. Min Act: -0.0003

Data Index: 803241 (C4 (Web Text))

Max Activating Token Index: 83

Text #11

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4318. Min Act: -0.0003

Data Index: 393860 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4907. Min Act: -0.0003

Data Index: 377406 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4873. Min Act: -0.0003

Data Index: 38546 (C4 (Web Text))

Max Activating Token Index: 236

Text #14

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4704. Min Act: -0.0003

Data Index: 864175 (C4 (Web Text))

Max Activating Token Index: 1019

Text #15

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4855. Min Act: -0.0003

Data Index: 451062 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4534. Min Act: -0.0003

Data Index: 175205 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4669. Min Act: -0.0003

Data Index: 1232219 (C4 (Web Text))

Max Activating Token Index: 85

Text #18

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4787. Min Act: -0.0003

Data Index: 675774 (C4 (Web Text))

Max Activating Token Index: 467

Text #19

Max Range: 0.5973. Min Range: -0.5973

Max Act: 0.4818. Min Act: -0.0003

Data Index: 1037531 (C4 (Web Text))

Max Activating Token Index: 178