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

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

Neuron 5318 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2818. Min Act: -0.0002

Data Index: 560988 (C4 (Web Text))

Max Activating Token Index: 22

Text #1

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2816. Min Act: -0.0002

Data Index: 555660 (C4 (Web Text))

Max Activating Token Index: 2

Text #2

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2816. Min Act: -0.0002

Data Index: 409942 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2820. Min Act: -0.0002

Data Index: 58032 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2260. Min Act: -0.0002

Data Index: 961497 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2929. Min Act: -0.0002

Data Index: 12488 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2297. Min Act: -0.0002

Data Index: 226639 (C4 (Web Text))

Max Activating Token Index: 9

Text #7

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2503. Min Act: -0.0002

Data Index: 559605 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2276. Min Act: -0.0002

Data Index: 1164645 (C4 (Web Text))

Max Activating Token Index: 3

Text #9

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2430. Min Act: -0.0002

Data Index: 740758 (C4 (Web Text))

Max Activating Token Index: 15

Text #10

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.2008. Min Act: -0.0002

Data Index: 1130230 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1933. Min Act: -0.0003

Data Index: 1194385 (C4 (Web Text))

Max Activating Token Index: 3

Text #12

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1779. Min Act: -0.0002

Data Index: 831449 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1749. Min Act: -0.0002

Data Index: 938331 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1968. Min Act: -0.0002

Data Index: 622847 (C4 (Web Text))

Max Activating Token Index: 4

Text #15

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1736. Min Act: -0.0003

Data Index: 1019511 (C4 (Web Text))

Max Activating Token Index: 141

Text #16

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1828. Min Act: -0.0002

Data Index: 294214 (C4 (Web Text))

Max Activating Token Index: 88

Text #17

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1770. Min Act: -0.0002

Data Index: 643730 (C4 (Web Text))

Max Activating Token Index: 79

Text #18

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1760. Min Act: -0.0003

Data Index: 1060718 (C4 (Web Text))

Max Activating Token Index: 59

Text #19

Max Range: 1.2929. Min Range: -1.2929

Max Act: 1.1824. Min Act: -0.0002

Data Index: 972943 (C4 (Web Text))

Max Activating Token Index: 137