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

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

Neuron 1697 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.7146. Min Act: -0.0000

Data Index: 306765 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.5437. Min Act: -0.0000

Data Index: 1233620 (C4 (Web Text))

Max Activating Token Index: 507

Text #2

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.5426. Min Act: -0.0000

Data Index: 1158353 (C4 (Web Text))

Max Activating Token Index: 446

Text #3

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4771. Min Act: -0.0000

Data Index: 120219 (C4 (Web Text))

Max Activating Token Index: 741

Text #4

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4826. Min Act: -0.0000

Data Index: 681039 (C4 (Web Text))

Max Activating Token Index: 231

Text #5

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4986. Min Act: -0.0000

Data Index: 576027 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4437. Min Act: -0.0000

Data Index: 335355 (C4 (Web Text))

Max Activating Token Index: 531

Text #7

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3918. Min Act: -0.0000

Data Index: 1089856 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4227. Min Act: -0.0000

Data Index: 415044 (C4 (Web Text))

Max Activating Token Index: 141

Text #9

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3998. Min Act: -0.0000

Data Index: 1211074 (C4 (Web Text))

Max Activating Token Index: 752

Text #10

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4118. Min Act: -0.0000

Data Index: 1338002 (C4 (Web Text))

Max Activating Token Index: 256

Text #11

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4161. Min Act: -0.0000

Data Index: 1885 (C4 (Web Text))

Max Activating Token Index: 809

Text #12

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.4071. Min Act: -0.0000

Data Index: 125239 (C4 (Web Text))

Max Activating Token Index: 775

Text #13

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3754. Min Act: -0.0000

Data Index: 895799 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3957. Min Act: -0.0000

Data Index: 146579 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3898. Min Act: -0.0001

Data Index: 1607327 (Python Code)

Max Activating Token Index: 887

Text #16

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3796. Min Act: -0.0000

Data Index: 1352387 (C4 (Web Text))

Max Activating Token Index: 285

Text #17

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3648. Min Act: -0.0000

Data Index: 727760 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3868. Min Act: -0.0000

Data Index: 1177998 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 0.7146. Min Range: -0.7146

Max Act: 0.3571. Min Act: -0.0000

Data Index: 161270 (C4 (Web Text))

Max Activating Token Index: 175