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

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

Neuron 2516 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2944. Min Range: -2.2944

Max Act: 2.2944. Min Act: -0.0000

Data Index: 1538304 (Python Code)

Max Activating Token Index: 46

Text #1

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.9937. Min Act: -0.0000

Data Index: 1617791 (Python Code)

Max Activating Token Index: 214

Text #2

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.7738. Min Act: -0.0000

Data Index: 1412038 (Python Code)

Max Activating Token Index: 612

Text #3

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.8579. Min Act: -0.0000

Data Index: 1532086 (Python Code)

Max Activating Token Index: 489

Text #4

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.7483. Min Act: -0.0000

Data Index: 1450114 (Python Code)

Max Activating Token Index: 207

Text #5

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.7529. Min Act: -0.0000

Data Index: 1446395 (Python Code)

Max Activating Token Index: 145

Text #6

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.6885. Min Act: -0.0000

Data Index: 1364358 (Python Code)

Max Activating Token Index: 274

Text #7

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.6520. Min Act: -0.0000

Data Index: 1429109 (Python Code)

Max Activating Token Index: 213

Text #8

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5541. Min Act: -0.0000

Data Index: 1584943 (Python Code)

Max Activating Token Index: 318

Text #9

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5481. Min Act: -0.0000

Data Index: 1367321 (Python Code)

Max Activating Token Index: 439

Text #10

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.6337. Min Act: -0.0000

Data Index: 1494762 (Python Code)

Max Activating Token Index: 491

Text #11

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.7024. Min Act: -0.0000

Data Index: 1621245 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5941. Min Act: -0.0000

Data Index: 1501724 (Python Code)

Max Activating Token Index: 771

Text #13

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5910. Min Act: -0.0000

Data Index: 1416733 (Python Code)

Max Activating Token Index: 115

Text #14

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5724. Min Act: -0.0000

Data Index: 1507136 (Python Code)

Max Activating Token Index: 131

Text #15

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5602. Min Act: -0.0000

Data Index: 1650573 (Python Code)

Max Activating Token Index: 22

Text #16

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5541. Min Act: -0.0000

Data Index: 1481713 (Python Code)

Max Activating Token Index: 404

Text #17

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.4492. Min Act: -0.0000

Data Index: 1599834 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5287. Min Act: -0.0000

Data Index: 1600485 (Python Code)

Max Activating Token Index: 595

Text #19

Max Range: 2.2944. Min Range: -2.2944

Max Act: 1.5031. Min Act: -0.0000

Data Index: 1371635 (Python Code)

Max Activating Token Index: 261