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

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

Neuron 2626 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: 2.4299. Min Range: -2.4299

Max Act: 2.4299. Min Act: -0.0000

Data Index: 62896 (C4 (Web Text))

Max Activating Token Index: 994

Text #1

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.8342. Min Act: -0.0000

Data Index: 756193 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 2.4299. Min Range: -2.4299

Max Act: 2.0102. Min Act: -0.0000

Data Index: 270503 (C4 (Web Text))

Max Activating Token Index: 388

Text #3

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.8657. Min Act: -0.0000

Data Index: 613242 (C4 (Web Text))

Max Activating Token Index: 848

Text #4

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.9042. Min Act: -0.0000

Data Index: 640764 (C4 (Web Text))

Max Activating Token Index: 775

Text #5

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.9052. Min Act: -0.0000

Data Index: 323816 (C4 (Web Text))

Max Activating Token Index: 309

Text #6

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.7998. Min Act: -0.0000

Data Index: 183794 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.9787. Min Act: -0.0000

Data Index: 308060 (C4 (Web Text))

Max Activating Token Index: 886

Text #8

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.8793. Min Act: -0.0000

Data Index: 909255 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 2.4299. Min Range: -2.4299

Max Act: 2.0734. Min Act: -0.0000

Data Index: 1174651 (C4 (Web Text))

Max Activating Token Index: 663

Text #10

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.8538. Min Act: -0.0000

Data Index: 1351221 (C4 (Web Text))

Max Activating Token Index: 989

Text #11

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.8571. Min Act: -0.0000

Data Index: 50540 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.9540. Min Act: -0.0000

Data Index: 694103 (C4 (Web Text))

Max Activating Token Index: 839

Text #13

Max Range: 2.4299. Min Range: -2.4299

Max Act: 2.0375. Min Act: -0.0000

Data Index: 1243251 (C4 (Web Text))

Max Activating Token Index: 891

Text #14

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.8135. Min Act: -0.0000

Data Index: 1096931 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.9071. Min Act: -0.0000

Data Index: 997685 (C4 (Web Text))

Max Activating Token Index: 963

Text #16

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.8983. Min Act: -0.0000

Data Index: 722833 (C4 (Web Text))

Max Activating Token Index: 362

Text #17

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1271200 (C4 (Web Text))

Max Activating Token Index: 930

Text #18

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.7727. Min Act: -0.0000

Data Index: 598892 (C4 (Web Text))

Max Activating Token Index: 940

Text #19

Max Range: 2.4299. Min Range: -2.4299

Max Act: 1.6615. Min Act: -0.0000

Data Index: 291604 (C4 (Web Text))

Max Activating Token Index: 401