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

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

Neuron 5000 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0421. Min Act: -0.0001

Data Index: 658833 (C4 (Web Text))

Max Activating Token Index: 19

Text #1

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.2360. Min Act: -0.0001

Data Index: 880067 (C4 (Web Text))

Max Activating Token Index: 466

Text #2

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.1706. Min Act: -0.0001

Data Index: 46489 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.1676. Min Act: -0.0001

Data Index: 1286618 (C4 (Web Text))

Max Activating Token Index: 444

Text #4

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9260. Min Act: -0.0001

Data Index: 109466 (C4 (Web Text))

Max Activating Token Index: 801

Text #5

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.1526. Min Act: -0.0001

Data Index: 716892 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0064. Min Act: -0.0001

Data Index: 589115 (C4 (Web Text))

Max Activating Token Index: 663

Text #7

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0916. Min Act: -0.0001

Data Index: 490459 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8887. Min Act: -0.0001

Data Index: 519769 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9604. Min Act: -0.0001

Data Index: 1104755 (C4 (Web Text))

Max Activating Token Index: 768

Text #10

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0432. Min Act: -0.0001

Data Index: 87047 (C4 (Web Text))

Max Activating Token Index: 301

Text #11

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.1095. Min Act: -0.0001

Data Index: 1159398 (C4 (Web Text))

Max Activating Token Index: 958

Text #12

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9561. Min Act: -0.0001

Data Index: 63775 (C4 (Web Text))

Max Activating Token Index: 889

Text #13

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9649. Min Act: -0.0001

Data Index: 1319792 (C4 (Web Text))

Max Activating Token Index: 518

Text #14

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0590. Min Act: -0.0001

Data Index: 955547 (C4 (Web Text))

Max Activating Token Index: 316

Text #15

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.9918. Min Act: -0.0001

Data Index: 1329123 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0543. Min Act: -0.0001

Data Index: 1123817 (C4 (Web Text))

Max Activating Token Index: 373

Text #17

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8410. Min Act: -0.0001

Data Index: 1113766 (C4 (Web Text))

Max Activating Token Index: 176

Text #18

Max Range: 1.2360. Min Range: -1.2360

Max Act: 1.0817. Min Act: -0.0001

Data Index: 544851 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 1.2360. Min Range: -1.2360

Max Act: 0.8181. Min Act: -0.0001

Data Index: 1261961 (C4 (Web Text))

Max Activating Token Index: 774