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

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

Neuron 1588 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: 1.1174. Min Range: -1.1174

Max Act: 1.0243. Min Act: -0.0001

Data Index: 1031674 (C4 (Web Text))

Max Activating Token Index: 791

Text #1

Max Range: 1.1174. Min Range: -1.1174

Max Act: 1.1174. Min Act: -0.0001

Data Index: 401049 (C4 (Web Text))

Max Activating Token Index: 824

Text #2

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.9690. Min Act: -0.0001

Data Index: 1294892 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.9590. Min Act: -0.0001

Data Index: 193781 (C4 (Web Text))

Max Activating Token Index: 769

Text #4

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.9541. Min Act: -0.0001

Data Index: 604102 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.8750. Min Act: -0.0001

Data Index: 791579 (C4 (Web Text))

Max Activating Token Index: 896

Text #6

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.9189. Min Act: -0.0001

Data Index: 165243 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 1.1174. Min Range: -1.1174

Max Act: 1.0959. Min Act: -0.0001

Data Index: 890910 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.9408. Min Act: -0.0001

Data Index: 47628 (C4 (Web Text))

Max Activating Token Index: 721

Text #9

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.9323. Min Act: -0.0001

Data Index: 403980 (C4 (Web Text))

Max Activating Token Index: 121

Text #10

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.8756. Min Act: -0.0001

Data Index: 860101 (C4 (Web Text))

Max Activating Token Index: 377

Text #11

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.7798. Min Act: -0.0001

Data Index: 175704 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.7867. Min Act: -0.0001

Data Index: 446394 (C4 (Web Text))

Max Activating Token Index: 352

Text #13

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.7904. Min Act: -0.0001

Data Index: 89676 (C4 (Web Text))

Max Activating Token Index: 43

Text #14

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.8228. Min Act: -0.0001

Data Index: 303688 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.7828. Min Act: -0.0001

Data Index: 1056743 (C4 (Web Text))

Max Activating Token Index: 24

Text #16

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.7702. Min Act: -0.0001

Data Index: 1090689 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.7693. Min Act: -0.0001

Data Index: 1294912 (C4 (Web Text))

Max Activating Token Index: 803

Text #18

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.7386. Min Act: -0.0001

Data Index: 415138 (C4 (Web Text))

Max Activating Token Index: 333

Text #19

Max Range: 1.1174. Min Range: -1.1174

Max Act: 0.8029. Min Act: -0.0001

Data Index: 27514 (C4 (Web Text))

Max Activating Token Index: 436