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

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

Neuron 3396 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.1657. Min Act: -0.0003

Data Index: 1296946 (C4 (Web Text))

Max Activating Token Index: 35

Text #1

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.1175. Min Act: -0.0003

Data Index: 355026 (C4 (Web Text))

Max Activating Token Index: 640

Text #2

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.1168. Min Act: -0.0003

Data Index: 368482 (C4 (Web Text))

Max Activating Token Index: 161

Text #3

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.1621. Min Act: -0.0003

Data Index: 622948 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.1657. Min Range: -1.1657

Max Act: 1.0267. Min Act: -0.0003

Data Index: 37356 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9016. Min Act: -0.0003

Data Index: 1281825 (C4 (Web Text))

Max Activating Token Index: 758

Text #6

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9445. Min Act: -0.0003

Data Index: 1167776 (C4 (Web Text))

Max Activating Token Index: 859

Text #7

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9101. Min Act: -0.0003

Data Index: 130451 (C4 (Web Text))

Max Activating Token Index: 409

Text #8

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9197. Min Act: -0.0002

Data Index: 1069624 (C4 (Web Text))

Max Activating Token Index: 24

Text #9

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9791. Min Act: -0.0003

Data Index: 619674 (C4 (Web Text))

Max Activating Token Index: 60

Text #10

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9722. Min Act: -0.0003

Data Index: 504106 (C4 (Web Text))

Max Activating Token Index: 482

Text #11

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9685. Min Act: -0.0003

Data Index: 1056479 (C4 (Web Text))

Max Activating Token Index: 21

Text #12

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9349. Min Act: -0.0003

Data Index: 368531 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9323. Min Act: -0.0003

Data Index: 932680 (C4 (Web Text))

Max Activating Token Index: 18

Text #14

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8993. Min Act: -0.0003

Data Index: 181415 (C4 (Web Text))

Max Activating Token Index: 42

Text #15

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9481. Min Act: -0.0003

Data Index: 340231 (C4 (Web Text))

Max Activating Token Index: 895

Text #16

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8879. Min Act: -0.0003

Data Index: 175487 (C4 (Web Text))

Max Activating Token Index: 30

Text #17

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8552. Min Act: -0.0003

Data Index: 541302 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.9640. Min Act: -0.0002

Data Index: 623914 (C4 (Web Text))

Max Activating Token Index: 694

Text #19

Max Range: 1.1657. Min Range: -1.1657

Max Act: 0.8796. Min Act: -0.0002

Data Index: 538847 (C4 (Web Text))

Max Activating Token Index: 868