Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1161 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.9018. Min Act: -0.0000

Data Index: 1198866 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.6952. Min Act: -0.0000

Data Index: 954757 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.2631. Min Act: -0.0000

Data Index: 197014 (C4 (Web Text))

Max Activating Token Index: 334

Text #3

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.1837. Min Act: -0.0000

Data Index: 1340587 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.7915. Min Act: -0.0000

Data Index: 1052739 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.3488. Min Act: -0.0000

Data Index: 95538 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.2871. Min Act: -0.0000

Data Index: 222711 (C4 (Web Text))

Max Activating Token Index: 8

Text #7

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.2438. Min Act: -0.0000

Data Index: 590286 (C4 (Web Text))

Max Activating Token Index: 381

Text #8

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.1972. Min Act: -0.0000

Data Index: 973555 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.0068. Min Act: -0.0000

Data Index: 105545 (C4 (Web Text))

Max Activating Token Index: 662

Text #10

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.1543. Min Act: -0.0000

Data Index: 1115730 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 3.9018. Min Range: -3.9018

Max Act: 2.9874. Min Act: -0.0000

Data Index: 1073135 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 3.9018. Min Range: -3.9018

Max Act: 2.9550. Min Act: -0.0000

Data Index: 293037 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.0720. Min Act: -0.0000

Data Index: 153220 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.0933. Min Act: -0.0000

Data Index: 73532 (C4 (Web Text))

Max Activating Token Index: 76

Text #15

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.0970. Min Act: -0.0000

Data Index: 191979 (C4 (Web Text))

Max Activating Token Index: 601

Text #16

Max Range: 3.9018. Min Range: -3.9018

Max Act: 2.3096. Min Act: -0.0000

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 861

Text #17

Max Range: 3.9018. Min Range: -3.9018

Max Act: 2.9140. Min Act: -0.0000

Data Index: 544904 (C4 (Web Text))

Max Activating Token Index: 992

Text #18

Max Range: 3.9018. Min Range: -3.9018

Max Act: 3.0323. Min Act: -0.0000

Data Index: 944796 (C4 (Web Text))

Max Activating Token Index: 650

Text #19

Max Range: 3.9018. Min Range: -3.9018

Max Act: 2.7521. Min Act: -0.0000

Data Index: 1134680 (C4 (Web Text))

Max Activating Token Index: 941