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

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

Neuron 3201 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2628. Min Act: -0.0000

Data Index: 917356 (C4 (Web Text))

Max Activating Token Index: 928

Text #1

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2684. Min Act: -0.0000

Data Index: 626995 (C4 (Web Text))

Max Activating Token Index: 903

Text #2

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2206. Min Act: -0.0000

Data Index: 743653 (C4 (Web Text))

Max Activating Token Index: 212

Text #3

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2226. Min Act: -0.0000

Data Index: 481181 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2033. Min Act: -0.0000

Data Index: 202903 (C4 (Web Text))

Max Activating Token Index: 309

Text #5

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2007. Min Act: -0.0000

Data Index: 1070872 (C4 (Web Text))

Max Activating Token Index: 303

Text #6

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2085. Min Act: -0.0000

Data Index: 495111 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.2004. Min Act: -0.0000

Data Index: 1149102 (C4 (Web Text))

Max Activating Token Index: 624

Text #8

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1983. Min Act: -0.0000

Data Index: 121858 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1953. Min Act: -0.0000

Data Index: 591288 (C4 (Web Text))

Max Activating Token Index: 758

Text #10

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1862. Min Act: -0.0000

Data Index: 972599 (C4 (Web Text))

Max Activating Token Index: 732

Text #11

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1895. Min Act: -0.0000

Data Index: 661537 (C4 (Web Text))

Max Activating Token Index: 864

Text #12

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1821. Min Act: -0.0000

Data Index: 743825 (C4 (Web Text))

Max Activating Token Index: 660

Text #13

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1939. Min Act: -0.0000

Data Index: 949398 (C4 (Web Text))

Max Activating Token Index: 937

Text #14

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1704. Min Act: -0.0000

Data Index: 339226 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1772. Min Act: -0.0000

Data Index: 390347 (C4 (Web Text))

Max Activating Token Index: 437

Text #16

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1765. Min Act: -0.0000

Data Index: 244955 (C4 (Web Text))

Max Activating Token Index: 220

Text #17

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1470. Min Act: -0.0000

Data Index: 424321 (C4 (Web Text))

Max Activating Token Index: 741

Text #18

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1829. Min Act: -0.0000

Data Index: 1179477 (C4 (Web Text))

Max Activating Token Index: 153

Text #19

Max Range: 0.2684. Min Range: -0.2684

Max Act: 0.1792. Min Act: -0.0000

Data Index: 922259 (C4 (Web Text))

Max Activating Token Index: 893