Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3621 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2916. Min Act: -0.0002

Data Index: 664951 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2618. Min Act: -0.0001

Data Index: 1187749 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2618. Min Act: -0.0002

Data Index: 96923 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2602. Min Act: -0.0002

Data Index: 55175 (C4 (Web Text))

Max Activating Token Index: 49

Text #4

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2460. Min Act: -0.0001

Data Index: 142226 (C4 (Web Text))

Max Activating Token Index: 36

Text #5

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2456. Min Act: -0.0001

Data Index: 1230391 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2535. Min Act: -0.0001

Data Index: 474373 (C4 (Web Text))

Max Activating Token Index: 10

Text #7

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2535. Min Act: -0.0001

Data Index: 1227298 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2535. Min Act: -0.0001

Data Index: 865110 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2535. Min Act: -0.0001

Data Index: 323822 (C4 (Web Text))

Max Activating Token Index: 10

Text #10

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2582. Min Act: -0.0002

Data Index: 137660 (C4 (Web Text))

Max Activating Token Index: 9

Text #11

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2322. Min Act: -0.0002

Data Index: 744960 (C4 (Web Text))

Max Activating Token Index: 30

Text #12

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2552. Min Act: -0.0002

Data Index: 918500 (C4 (Web Text))

Max Activating Token Index: 53

Text #13

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2459. Min Act: -0.0002

Data Index: 561684 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2471. Min Act: -0.0002

Data Index: 732073 (C4 (Web Text))

Max Activating Token Index: 23

Text #15

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2302. Min Act: -0.0001

Data Index: 1321242 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2531. Min Act: -0.0002

Data Index: 500463 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2418. Min Act: -0.0001

Data Index: 1027060 (C4 (Web Text))

Max Activating Token Index: 22

Text #18

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2508. Min Act: -0.0001

Data Index: 876192 (C4 (Web Text))

Max Activating Token Index: 578

Text #19

Max Range: 0.2916. Min Range: -0.2916

Max Act: 0.2345. Min Act: -0.0001

Data Index: 133715 (C4 (Web Text))

Max Activating Token Index: 8