Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1784 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8402. Min Act: -0.0001

Data Index: 1567036 (Python Code)

Max Activating Token Index: 460

Text #1

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8317. Min Act: -0.0001

Data Index: 1549315 (Python Code)

Max Activating Token Index: 128

Text #2

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7943. Min Act: -0.0001

Data Index: 1496043 (Python Code)

Max Activating Token Index: 483

Text #3

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7711. Min Act: -0.0001

Data Index: 1499889 (Python Code)

Max Activating Token Index: 400

Text #4

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7989. Min Act: -0.0001

Data Index: 1591530 (Python Code)

Max Activating Token Index: 552

Text #5

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.8035. Min Act: -0.0001

Data Index: 1537412 (Python Code)

Max Activating Token Index: 629

Text #6

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7249. Min Act: -0.0001

Data Index: 1454826 (Python Code)

Max Activating Token Index: 900

Text #7

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7624. Min Act: -0.0001

Data Index: 1513654 (Python Code)

Max Activating Token Index: 80

Text #8

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7544. Min Act: -0.0001

Data Index: 1395843 (Python Code)

Max Activating Token Index: 185

Text #9

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7502. Min Act: -0.0001

Data Index: 1424584 (Python Code)

Max Activating Token Index: 382

Text #10

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7737. Min Act: -0.0001

Data Index: 1442471 (Python Code)

Max Activating Token Index: 981

Text #11

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7518. Min Act: -0.0001

Data Index: 1464458 (Python Code)

Max Activating Token Index: 715

Text #12

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7578. Min Act: -0.0001

Data Index: 1379701 (Python Code)

Max Activating Token Index: 55

Text #13

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7589. Min Act: -0.0001

Data Index: 1487564 (Python Code)

Max Activating Token Index: 393

Text #14

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7579. Min Act: -0.0001

Data Index: 1394466 (Python Code)

Max Activating Token Index: 120

Text #15

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7797. Min Act: -0.0001

Data Index: 1569691 (Python Code)

Max Activating Token Index: 788

Text #16

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7546. Min Act: -0.0002

Data Index: 1431804 (Python Code)

Max Activating Token Index: 973

Text #17

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7755. Min Act: -0.0001

Data Index: 1392217 (Python Code)

Max Activating Token Index: 564

Text #18

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.6967. Min Act: -0.0001

Data Index: 1429002 (Python Code)

Max Activating Token Index: 387

Text #19

Max Range: 0.8402. Min Range: -0.8402

Max Act: 0.7138. Min Act: -0.0001

Data Index: 1425038 (Python Code)

Max Activating Token Index: 1016