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

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

Neuron 1178 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1393. Min Act: -0.0001

Data Index: 1582790 (Python Code)

Max Activating Token Index: 778

Text #1

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1263. Min Act: -0.0001

Data Index: 1501337 (Python Code)

Max Activating Token Index: 141

Text #2

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1170. Min Act: -0.0001

Data Index: 1439089 (Python Code)

Max Activating Token Index: 714

Text #3

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1155. Min Act: -0.0001

Data Index: 1656576 (Python Code)

Max Activating Token Index: 730

Text #4

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1641224 (Python Code)

Max Activating Token Index: 694

Text #5

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1116. Min Act: -0.0001

Data Index: 1548439 (Python Code)

Max Activating Token Index: 586

Text #6

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1152. Min Act: -0.0001

Data Index: 1417786 (Python Code)

Max Activating Token Index: 457

Text #7

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1169. Min Act: -0.0001

Data Index: 1636287 (Python Code)

Max Activating Token Index: 790

Text #8

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1128. Min Act: -0.0001

Data Index: 1540908 (Python Code)

Max Activating Token Index: 804

Text #9

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1083. Min Act: -0.0001

Data Index: 1636038 (Python Code)

Max Activating Token Index: 384

Text #10

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1089. Min Act: -0.0001

Data Index: 1602703 (Python Code)

Max Activating Token Index: 399

Text #11

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1049. Min Act: -0.0001

Data Index: 1495162 (Python Code)

Max Activating Token Index: 619

Text #12

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1075. Min Act: -0.0001

Data Index: 1391792 (Python Code)

Max Activating Token Index: 501

Text #13

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1094. Min Act: -0.0001

Data Index: 1394108 (Python Code)

Max Activating Token Index: 512

Text #14

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1082. Min Act: -0.0001

Data Index: 1621308 (Python Code)

Max Activating Token Index: 881

Text #15

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1039. Min Act: -0.0001

Data Index: 1533453 (Python Code)

Max Activating Token Index: 844

Text #16

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0944. Min Act: -0.0001

Data Index: 1440386 (Python Code)

Max Activating Token Index: 289

Text #17

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0999. Min Act: -0.0001

Data Index: 1473279 (Python Code)

Max Activating Token Index: 370

Text #18

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.1073. Min Act: -0.0001

Data Index: 1454082 (Python Code)

Max Activating Token Index: 963

Text #19

Max Range: 0.1393. Min Range: -0.1393

Max Act: 0.0989. Min Act: -0.0001

Data Index: 1548573 (Python Code)

Max Activating Token Index: 605