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

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

Neuron 2840 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: 1.5536. Min Range: -1.5536

Max Act: 1.4151. Min Act: -0.0001

Data Index: 185971 (C4 (Web Text))

Max Activating Token Index: 155

Text #1

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.5536. Min Act: -0.0001

Data Index: 194416 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.4248. Min Act: -0.0001

Data Index: 769624 (C4 (Web Text))

Max Activating Token Index: 768

Text #3

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.2261. Min Act: -0.0001

Data Index: 1105981 (C4 (Web Text))

Max Activating Token Index: 920

Text #4

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.4298. Min Act: -0.0001

Data Index: 1100494 (C4 (Web Text))

Max Activating Token Index: 824

Text #5

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.2535. Min Act: -0.0001

Data Index: 108311 (C4 (Web Text))

Max Activating Token Index: 97

Text #6

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1991. Min Act: -0.0001

Data Index: 791309 (C4 (Web Text))

Max Activating Token Index: 392

Text #7

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.2993. Min Act: -0.0001

Data Index: 1312709 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.3317. Min Act: -0.0001

Data Index: 1344618 (C4 (Web Text))

Max Activating Token Index: 376

Text #9

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1198. Min Act: -0.0001

Data Index: 715483 (C4 (Web Text))

Max Activating Token Index: 927

Text #10

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1405. Min Act: -0.0001

Data Index: 731369 (C4 (Web Text))

Max Activating Token Index: 307

Text #11

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1191. Min Act: -0.0001

Data Index: 14203 (C4 (Web Text))

Max Activating Token Index: 831

Text #12

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1720. Min Act: -0.0001

Data Index: 1210766 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.0163. Min Act: -0.0001

Data Index: 876539 (C4 (Web Text))

Max Activating Token Index: 872

Text #14

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.2988. Min Act: -0.0001

Data Index: 299635 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1309. Min Act: -0.0001

Data Index: 292835 (C4 (Web Text))

Max Activating Token Index: 703

Text #16

Max Range: 1.5536. Min Range: -1.5536

Max Act: 0.9829. Min Act: -0.0001

Data Index: 438073 (C4 (Web Text))

Max Activating Token Index: 269

Text #17

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1403. Min Act: -0.0001

Data Index: 150441 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.1385. Min Act: -0.0001

Data Index: 264364 (C4 (Web Text))

Max Activating Token Index: 158

Text #19

Max Range: 1.5536. Min Range: -1.5536

Max Act: 1.0419. Min Act: -0.0001

Data Index: 1213847 (C4 (Web Text))

Max Activating Token Index: 869