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

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

Neuron 3606 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: 0.7717. Min Range: -0.7717

Max Act: 0.7717. Min Act: -0.0000

Data Index: 1942 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.7486. Min Act: -0.0000

Data Index: 86035 (C4 (Web Text))

Max Activating Token Index: 39

Text #2

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6772. Min Act: -0.0001

Data Index: 895241 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6541. Min Act: -0.0001

Data Index: 852615 (C4 (Web Text))

Max Activating Token Index: 814

Text #4

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5926. Min Act: -0.0001

Data Index: 842908 (C4 (Web Text))

Max Activating Token Index: 695

Text #5

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.6093. Min Act: -0.0001

Data Index: 207789 (C4 (Web Text))

Max Activating Token Index: 202

Text #6

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5712. Min Act: -0.0000

Data Index: 953901 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5391. Min Act: -0.0001

Data Index: 300093 (C4 (Web Text))

Max Activating Token Index: 168

Text #8

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5329. Min Act: -0.0001

Data Index: 1248280 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5375. Min Act: -0.0000

Data Index: 52168 (C4 (Web Text))

Max Activating Token Index: 430

Text #10

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5099. Min Act: -0.0001

Data Index: 1309892 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5189. Min Act: -0.0001

Data Index: 608267 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5029. Min Act: -0.0001

Data Index: 245457 (C4 (Web Text))

Max Activating Token Index: 230

Text #13

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5154. Min Act: -0.0001

Data Index: 966403 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.4818. Min Act: -0.0000

Data Index: 865199 (C4 (Web Text))

Max Activating Token Index: 122

Text #15

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.4685. Min Act: -0.0001

Data Index: 145852 (C4 (Web Text))

Max Activating Token Index: 351

Text #16

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.4922. Min Act: -0.0000

Data Index: 438696 (C4 (Web Text))

Max Activating Token Index: 554

Text #17

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.4845. Min Act: -0.0001

Data Index: 1133155 (C4 (Web Text))

Max Activating Token Index: 123

Text #18

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5213. Min Act: -0.0001

Data Index: 891914 (C4 (Web Text))

Max Activating Token Index: 14

Text #19

Max Range: 0.7717. Min Range: -0.7717

Max Act: 0.5030. Min Act: -0.0001

Data Index: 1261836 (C4 (Web Text))

Max Activating Token Index: 930