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

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

Neuron 1228 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.5909. Min Act: -0.0000

Data Index: 1066882 (C4 (Web Text))

Max Activating Token Index: 874

Text #1

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.2396. Min Act: -0.0000

Data Index: 489022 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.1640. Min Act: -0.0000

Data Index: 337284 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 1.5909. Min Range: -1.5909

Max Act: 1.0746. Min Act: -0.0000

Data Index: 780495 (C4 (Web Text))

Max Activating Token Index: 606

Text #4

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9277. Min Act: -0.0000

Data Index: 1045268 (C4 (Web Text))

Max Activating Token Index: 946

Text #5

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9175. Min Act: -0.0000

Data Index: 631559 (C4 (Web Text))

Max Activating Token Index: 247

Text #6

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.9352. Min Act: -0.0000

Data Index: 990111 (C4 (Web Text))

Max Activating Token Index: 927

Text #7

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8364. Min Act: -0.0000

Data Index: 66368 (C4 (Web Text))

Max Activating Token Index: 969

Text #8

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7850. Min Act: -0.0000

Data Index: 209037 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8104. Min Act: -0.0001

Data Index: 1076896 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8072. Min Act: -0.0000

Data Index: 340916 (C4 (Web Text))

Max Activating Token Index: 979

Text #11

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8027. Min Act: -0.0000

Data Index: 543296 (C4 (Web Text))

Max Activating Token Index: 429

Text #12

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7899. Min Act: -0.0000

Data Index: 924489 (C4 (Web Text))

Max Activating Token Index: 52

Text #13

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7619. Min Act: -0.0000

Data Index: 1318025 (C4 (Web Text))

Max Activating Token Index: 1007

Text #14

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.8107. Min Act: -0.0000

Data Index: 40583 (C4 (Web Text))

Max Activating Token Index: 325

Text #15

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7609. Min Act: -0.0000

Data Index: 548595 (C4 (Web Text))

Max Activating Token Index: 930

Text #16

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7776. Min Act: -0.0000

Data Index: 686875 (C4 (Web Text))

Max Activating Token Index: 455

Text #17

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7676. Min Act: -0.0000

Data Index: 1139808 (C4 (Web Text))

Max Activating Token Index: 33

Text #18

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7629. Min Act: -0.0000

Data Index: 945325 (C4 (Web Text))

Max Activating Token Index: 951

Text #19

Max Range: 1.5909. Min Range: -1.5909

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1031286 (C4 (Web Text))

Max Activating Token Index: 731