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

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

Neuron 1783 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: 0.2408. Min Range: -0.2408

Max Act: 0.2408. Min Act: -0.0000

Data Index: 640578 (C4 (Web Text))

Max Activating Token Index: 442

Text #1

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2105. Min Act: -0.0000

Data Index: 713297 (C4 (Web Text))

Max Activating Token Index: 278

Text #2

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2031. Min Act: -0.0000

Data Index: 1252218 (C4 (Web Text))

Max Activating Token Index: 882

Text #3

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2117. Min Act: -0.0000

Data Index: 160285 (C4 (Web Text))

Max Activating Token Index: 924

Text #4

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2030. Min Act: -0.0000

Data Index: 25331 (C4 (Web Text))

Max Activating Token Index: 802

Text #5

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2077. Min Act: -0.0000

Data Index: 73054 (C4 (Web Text))

Max Activating Token Index: 92

Text #6

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2051. Min Act: -0.0000

Data Index: 388186 (C4 (Web Text))

Max Activating Token Index: 904

Text #7

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1166967 (C4 (Web Text))

Max Activating Token Index: 384

Text #8

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.2004. Min Act: -0.0000

Data Index: 3807 (C4 (Web Text))

Max Activating Token Index: 287

Text #9

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1832. Min Act: -0.0000

Data Index: 252329 (C4 (Web Text))

Max Activating Token Index: 606

Text #10

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1710. Min Act: -0.0000

Data Index: 1044397 (C4 (Web Text))

Max Activating Token Index: 130

Text #11

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1812. Min Act: -0.0001

Data Index: 668414 (C4 (Web Text))

Max Activating Token Index: 123

Text #12

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1776. Min Act: -0.0001

Data Index: 454306 (C4 (Web Text))

Max Activating Token Index: 240

Text #13

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1894. Min Act: -0.0000

Data Index: 107465 (C4 (Web Text))

Max Activating Token Index: 638

Text #14

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1722. Min Act: -0.0001

Data Index: 1357029 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1788. Min Act: -0.0000

Data Index: 368114 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1722. Min Act: -0.0001

Data Index: 826589 (C4 (Web Text))

Max Activating Token Index: 412

Text #17

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1641. Min Act: -0.0001

Data Index: 256690 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1183527 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.2408. Min Range: -0.2408

Max Act: 0.1593. Min Act: -0.0000

Data Index: 921510 (C4 (Web Text))

Max Activating Token Index: 558