Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4837 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1215. Min Range: -2.1215

Max Act: 2.1215. Min Act: -0.0000

Data Index: 432223 (C4 (Web Text))

Max Activating Token Index: 412

Text #1

Max Range: 2.1215. Min Range: -2.1215

Max Act: 2.0875. Min Act: -0.0000

Data Index: 542975 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 2.1215. Min Range: -2.1215

Max Act: 2.0869. Min Act: -0.0000

Data Index: 1422788 (Python Code)

Max Activating Token Index: 305

Text #3

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.8508. Min Act: -0.0000

Data Index: 1560616 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.7420. Min Act: -0.0000

Data Index: 1365194 (Python Code)

Max Activating Token Index: 895

Text #5

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.8883. Min Act: -0.0000

Data Index: 1430872 (Python Code)

Max Activating Token Index: 953

Text #6

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.6108. Min Act: -0.0000

Data Index: 1280699 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.5652. Min Act: -0.0000

Data Index: 218576 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.5546. Min Act: -0.0000

Data Index: 1303404 (C4 (Web Text))

Max Activating Token Index: 612

Text #9

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.6473. Min Act: -0.0000

Data Index: 1211508 (C4 (Web Text))

Max Activating Token Index: 989

Text #10

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.6989. Min Act: -0.0000

Data Index: 1623112 (Python Code)

Max Activating Token Index: 325

Text #11

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.5983. Min Act: -0.0000

Data Index: 1169610 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.5779. Min Act: -0.0000

Data Index: 1373725 (Python Code)

Max Activating Token Index: 250

Text #13

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.2459. Min Act: -0.0000

Data Index: 1426283 (Python Code)

Max Activating Token Index: 259

Text #14

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.5945. Min Act: -0.0000

Data Index: 1488785 (Python Code)

Max Activating Token Index: 354

Text #15

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.3942. Min Act: -0.0000

Data Index: 949078 (C4 (Web Text))

Max Activating Token Index: 624

Text #16

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.4445. Min Act: -0.0000

Data Index: 961309 (C4 (Web Text))

Max Activating Token Index: 745

Text #17

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.4910. Min Act: -0.0000

Data Index: 1448678 (Python Code)

Max Activating Token Index: 145

Text #18

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.3631. Min Act: -0.0000

Data Index: 1613640 (Python Code)

Max Activating Token Index: 60

Text #19

Max Range: 2.1215. Min Range: -2.1215

Max Act: 1.3475. Min Act: -0.0000

Data Index: 1449066 (Python Code)

Max Activating Token Index: 624