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

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

Neuron 4050 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1144. Min Act: -0.0000

Data Index: 75728 (C4 (Web Text))

Max Activating Token Index: 91

Text #1

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1074. Min Act: -0.0000

Data Index: 1254969 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1074. Min Act: -0.0000

Data Index: 573138 (C4 (Web Text))

Max Activating Token Index: 358

Text #3

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0989. Min Act: -0.0000

Data Index: 280717 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1121385 (C4 (Web Text))

Max Activating Token Index: 661

Text #5

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1001. Min Act: -0.0000

Data Index: 743497 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.1013. Min Act: -0.0001

Data Index: 629198 (C4 (Web Text))

Max Activating Token Index: 875

Text #7

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0904. Min Act: -0.0000

Data Index: 1290399 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0871. Min Act: -0.0000

Data Index: 605553 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0897. Min Act: -0.0000

Data Index: 557504 (C4 (Web Text))

Max Activating Token Index: 578

Text #10

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0855. Min Act: -0.0001

Data Index: 24239 (C4 (Web Text))

Max Activating Token Index: 292

Text #11

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0946. Min Act: -0.0000

Data Index: 927950 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1248582 (C4 (Web Text))

Max Activating Token Index: 521

Text #13

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0842. Min Act: -0.0000

Data Index: 273636 (C4 (Web Text))

Max Activating Token Index: 510

Text #14

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0873. Min Act: -0.0000

Data Index: 149634 (C4 (Web Text))

Max Activating Token Index: 257

Text #15

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1310638 (C4 (Web Text))

Max Activating Token Index: 1012

Text #16

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0901. Min Act: -0.0001

Data Index: 1099312 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0837. Min Act: -0.0000

Data Index: 45475 (C4 (Web Text))

Max Activating Token Index: 104

Text #18

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0829. Min Act: -0.0000

Data Index: 943020 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.1144. Min Range: -0.1144

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1034899 (C4 (Web Text))

Max Activating Token Index: 866