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

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

Neuron 447 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6780. Min Act: -0.0001

Data Index: 1607691 (Python Code)

Max Activating Token Index: 341

Text #1

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6547. Min Act: -0.0001

Data Index: 1447513 (Python Code)

Max Activating Token Index: 51

Text #2

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6228. Min Act: -0.0001

Data Index: 1396276 (Python Code)

Max Activating Token Index: 862

Text #3

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6195. Min Act: -0.0001

Data Index: 1430740 (Python Code)

Max Activating Token Index: 289

Text #4

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5915. Min Act: -0.0001

Data Index: 1389259 (Python Code)

Max Activating Token Index: 424

Text #5

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5550. Min Act: -0.0001

Data Index: 1537119 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5528. Min Act: -0.0001

Data Index: 1566411 (Python Code)

Max Activating Token Index: 139

Text #7

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5482. Min Act: -0.0001

Data Index: 1474232 (Python Code)

Max Activating Token Index: 22

Text #8

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5426. Min Act: -0.0001

Data Index: 1482949 (Python Code)

Max Activating Token Index: 384

Text #9

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5445. Min Act: -0.0001

Data Index: 1421637 (Python Code)

Max Activating Token Index: 602

Text #10

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.6077. Min Act: -0.0001

Data Index: 1610371 (Python Code)

Max Activating Token Index: 679

Text #11

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5121. Min Act: -0.0001

Data Index: 1492253 (Python Code)

Max Activating Token Index: 595

Text #12

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5198. Min Act: -0.0001

Data Index: 1366650 (Python Code)

Max Activating Token Index: 265

Text #13

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5432. Min Act: -0.0001

Data Index: 1368209 (Python Code)

Max Activating Token Index: 704

Text #14

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4763. Min Act: -0.0001

Data Index: 1638335 (Python Code)

Max Activating Token Index: 280

Text #15

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5225. Min Act: -0.0001

Data Index: 1400351 (Python Code)

Max Activating Token Index: 343

Text #16

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5182. Min Act: -0.0001

Data Index: 1450349 (Python Code)

Max Activating Token Index: 930

Text #17

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5276. Min Act: -0.0001

Data Index: 1526801 (Python Code)

Max Activating Token Index: 315

Text #18

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.4979. Min Act: -0.0001

Data Index: 1488349 (Python Code)

Max Activating Token Index: 996

Text #19

Max Range: 0.6780. Min Range: -0.6780

Max Act: 0.5462. Min Act: -0.0001

Data Index: 1468557 (Python Code)

Max Activating Token Index: 609