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

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

Neuron 4710 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.8626. Min Act: 0.0001

Data Index: 680027 (C4 (Web Text))

Max Activating Token Index: 37

Text #1

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.8687. Min Act: 0.0000

Data Index: 528957 (C4 (Web Text))

Max Activating Token Index: 16

Text #2

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.6519. Min Act: -0.0001

Data Index: 524944 (C4 (Web Text))

Max Activating Token Index: 177

Text #3

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.4831. Min Act: -0.0000

Data Index: 464875 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.4483. Min Act: -0.0000

Data Index: 733246 (C4 (Web Text))

Max Activating Token Index: 17

Text #5

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.4810. Min Act: 0.0000

Data Index: 251403 (C4 (Web Text))

Max Activating Token Index: 15

Text #6

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.4687. Min Act: -0.0000

Data Index: 10245 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.4841. Min Act: -0.0000

Data Index: 53820 (C4 (Web Text))

Max Activating Token Index: 99

Text #8

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.3305. Min Act: -0.0000

Data Index: 1006524 (C4 (Web Text))

Max Activating Token Index: 334

Text #9

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.4223. Min Act: -0.0000

Data Index: 362876 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.3245. Min Act: 0.0000

Data Index: 1014213 (C4 (Web Text))

Max Activating Token Index: 11

Text #11

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.3619. Min Act: -0.0000

Data Index: 775042 (C4 (Web Text))

Max Activating Token Index: 39

Text #12

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.3161. Min Act: -0.0000

Data Index: 684610 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.3696. Min Act: -0.0000

Data Index: 575163 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.2437. Min Act: -0.0000

Data Index: 137895 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.2826. Min Act: -0.0000

Data Index: 1085802 (C4 (Web Text))

Max Activating Token Index: 21

Text #16

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.2255. Min Act: 0.0001

Data Index: 735374 (C4 (Web Text))

Max Activating Token Index: 16

Text #17

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.2917. Min Act: -0.0000

Data Index: 1052374 (C4 (Web Text))

Max Activating Token Index: 36

Text #18

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.1294. Min Act: -0.0000

Data Index: 259294 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.8687. Min Range: -1.8687

Max Act: 1.2495. Min Act: -0.0001

Data Index: 1222333 (C4 (Web Text))

Max Activating Token Index: 795