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

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

Neuron 1861 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0012. Min Act: -0.0001

Data Index: 550805 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0001

Data Index: 1217616 (C4 (Web Text))

Max Activating Token Index: 392

Text #2

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0010. Min Act: -0.0001

Data Index: 998729 (C4 (Web Text))

Max Activating Token Index: 843

Text #3

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0008. Min Act: -0.0001

Data Index: 1401955 (Python Code)

Max Activating Token Index: 1021

Text #4

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0001

Data Index: 430087 (C4 (Web Text))

Max Activating Token Index: 168

Text #5

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0001

Data Index: 949231 (C4 (Web Text))

Max Activating Token Index: 818

Text #6

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0008. Min Act: -0.0001

Data Index: 1364051 (Python Code)

Max Activating Token Index: 378

Text #7

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0001

Data Index: 483025 (C4 (Web Text))

Max Activating Token Index: 582

Text #8

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0007. Min Act: -0.0001

Data Index: 38774 (C4 (Web Text))

Max Activating Token Index: 401

Text #9

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0001

Data Index: 1559739 (Python Code)

Max Activating Token Index: 992

Text #10

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0001

Data Index: 1608004 (Python Code)

Max Activating Token Index: 574

Text #11

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0006. Min Act: -0.0001

Data Index: 966265 (C4 (Web Text))

Max Activating Token Index: 301

Text #12

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1189332 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0001

Data Index: 492946 (C4 (Web Text))

Max Activating Token Index: 261

Text #14

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0003. Min Act: -0.0001

Data Index: 1520343 (Python Code)

Max Activating Token Index: 852

Text #15

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0001

Data Index: 1365762 (Python Code)

Max Activating Token Index: 296

Text #16

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0001

Data Index: 247232 (C4 (Web Text))

Max Activating Token Index: 939

Text #17

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0004. Min Act: -0.0001

Data Index: 824658 (C4 (Web Text))

Max Activating Token Index: 232

Text #18

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1588416 (Python Code)

Max Activating Token Index: 209

Text #19

Max Range: 0.0012. Min Range: -0.0012

Max Act: 0.0005. Min Act: -0.0001

Data Index: 1024337 (C4 (Web Text))

Max Activating Token Index: 531