Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 27 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1119081 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0571. Min Act: -0.0003

Data Index: 17785 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0578. Min Act: -0.0002

Data Index: 94179 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0565. Min Act: -0.0003

Data Index: 686410 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0529. Min Act: -0.0003

Data Index: 586118 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0543. Min Act: -0.0003

Data Index: 548495 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0534. Min Act: -0.0003

Data Index: 1282678 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0533. Min Act: -0.0003

Data Index: 204060 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1276511 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0534. Min Act: -0.0003

Data Index: 357343 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0530. Min Act: -0.0003

Data Index: 842087 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0531. Min Act: -0.0003

Data Index: 1279517 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0504. Min Act: -0.0003

Data Index: 968412 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0532. Min Act: -0.0003

Data Index: 1109474 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0519. Min Act: -0.0003

Data Index: 257805 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0519. Min Act: -0.0003

Data Index: 1049545 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0526. Min Act: -0.0003

Data Index: 659004 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0503. Min Act: -0.0003

Data Index: 221276 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0520. Min Act: -0.0003

Data Index: 281833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0604. Min Range: -0.0604

Max Act: 0.0525. Min Act: -0.0003

Data Index: 480724 (C4 (Web Text))

Max Activating Token Index: 1023