Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2982 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2738. Min Act: -0.0001

Data Index: 342155 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2675. Min Act: -0.0000

Data Index: 1182741 (C4 (Web Text))

Max Activating Token Index: 913

Text #2

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2275. Min Act: -0.0001

Data Index: 973343 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2210. Min Act: -0.0000

Data Index: 16776 (C4 (Web Text))

Max Activating Token Index: 333

Text #4

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2361. Min Act: -0.0001

Data Index: 665754 (C4 (Web Text))

Max Activating Token Index: 899

Text #5

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2284. Min Act: -0.0001

Data Index: 892384 (C4 (Web Text))

Max Activating Token Index: 745

Text #6

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2101. Min Act: -0.0001

Data Index: 905399 (C4 (Web Text))

Max Activating Token Index: 739

Text #7

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2053. Min Act: -0.0001

Data Index: 595408 (C4 (Web Text))

Max Activating Token Index: 894

Text #8

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2098. Min Act: -0.0001

Data Index: 1061855 (C4 (Web Text))

Max Activating Token Index: 636

Text #9

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2109. Min Act: -0.0001

Data Index: 99251 (C4 (Web Text))

Max Activating Token Index: 265

Text #10

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2030. Min Act: -0.0001

Data Index: 445956 (C4 (Web Text))

Max Activating Token Index: 554

Text #11

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2103. Min Act: -0.0001

Data Index: 533732 (C4 (Web Text))

Max Activating Token Index: 492

Text #12

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2011. Min Act: -0.0001

Data Index: 308396 (C4 (Web Text))

Max Activating Token Index: 551

Text #13

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1997. Min Act: -0.0000

Data Index: 1294420 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1975. Min Act: -0.0001

Data Index: 150935 (C4 (Web Text))

Max Activating Token Index: 203

Text #15

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2089. Min Act: -0.0001

Data Index: 332911 (C4 (Web Text))

Max Activating Token Index: 240

Text #16

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1873. Min Act: -0.0001

Data Index: 889165 (C4 (Web Text))

Max Activating Token Index: 866

Text #17

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1919. Min Act: -0.0001

Data Index: 243196 (C4 (Web Text))

Max Activating Token Index: 804

Text #18

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.1947. Min Act: -0.0001

Data Index: 163801 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.2738. Min Range: -0.2738

Max Act: 0.2082. Min Act: -0.0000

Data Index: 1326724 (C4 (Web Text))

Max Activating Token Index: 650