Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1143 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 3.8367. Min Range: -3.8367

Max Act: 3.8367. Min Act: -0.0001

Data Index: 1323634 (C4 (Web Text))

Max Activating Token Index: 14

Text #1

Max Range: 3.8367. Min Range: -3.8367

Max Act: 3.5641. Min Act: -0.0001

Data Index: 282898 (C4 (Web Text))

Max Activating Token Index: 18

Text #2

Max Range: 3.8367. Min Range: -3.8367

Max Act: 3.6181. Min Act: -0.0001

Data Index: 386338 (C4 (Web Text))

Max Activating Token Index: 34

Text #3

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.8953. Min Act: -0.0001

Data Index: 1211994 (C4 (Web Text))

Max Activating Token Index: 31

Text #4

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.8274. Min Act: -0.0001

Data Index: 81564 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.7008. Min Act: -0.0001

Data Index: 364622 (C4 (Web Text))

Max Activating Token Index: 10

Text #6

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.5902. Min Act: -0.0001

Data Index: 980783 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.7951. Min Act: -0.0001

Data Index: 1024898 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.4777. Min Act: -0.0001

Data Index: 472500 (C4 (Web Text))

Max Activating Token Index: 20

Text #9

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.4702. Min Act: -0.0001

Data Index: 640917 (C4 (Web Text))

Max Activating Token Index: 19

Text #10

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.6049. Min Act: -0.0001

Data Index: 138926 (C4 (Web Text))

Max Activating Token Index: 624

Text #11

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.4335. Min Act: -0.0001

Data Index: 641992 (C4 (Web Text))

Max Activating Token Index: 576

Text #12

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.2941. Min Act: -0.0001

Data Index: 408520 (C4 (Web Text))

Max Activating Token Index: 961

Text #13

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.2901. Min Act: -0.0001

Data Index: 1094368 (C4 (Web Text))

Max Activating Token Index: 31

Text #14

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.2550. Min Act: -0.0001

Data Index: 740552 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.2307. Min Act: -0.0001

Data Index: 686280 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.0264. Min Act: -0.0001

Data Index: 1156730 (C4 (Web Text))

Max Activating Token Index: 46

Text #17

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.1264. Min Act: -0.0001

Data Index: 1004879 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.2192. Min Act: -0.0001

Data Index: 1080653 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 3.8367. Min Range: -3.8367

Max Act: 2.0848. Min Act: -0.0001

Data Index: 990065 (C4 (Web Text))

Max Activating Token Index: 336