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

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

Neuron 4690 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.9971. Min Act: -0.0000

Data Index: 1447922 (Python Code)

Max Activating Token Index: 284

Text #1

Max Range: 3.3484. Min Range: -3.3484

Max Act: 3.3484. Min Act: -0.0000

Data Index: 1472316 (Python Code)

Max Activating Token Index: 526

Text #2

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.9618. Min Act: -0.0000

Data Index: 1463228 (Python Code)

Max Activating Token Index: 428

Text #3

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.9243. Min Act: -0.0000

Data Index: 1466850 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.9123. Min Act: -0.0000

Data Index: 1460096 (Python Code)

Max Activating Token Index: 815

Text #5

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.9155. Min Act: -0.0000

Data Index: 1495798 (Python Code)

Max Activating Token Index: 946

Text #6

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.9156. Min Act: -0.0000

Data Index: 1503940 (Python Code)

Max Activating Token Index: 723

Text #7

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.8596. Min Act: -0.0000

Data Index: 1569695 (Python Code)

Max Activating Token Index: 732

Text #8

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.7697. Min Act: -0.0000

Data Index: 1479256 (Python Code)

Max Activating Token Index: 555

Text #9

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.5962. Min Act: -0.0000

Data Index: 1478778 (Python Code)

Max Activating Token Index: 567

Text #10

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.7192. Min Act: -0.0000

Data Index: 1565272 (Python Code)

Max Activating Token Index: 588

Text #11

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.6118. Min Act: -0.0000

Data Index: 1610374 (Python Code)

Max Activating Token Index: 635

Text #12

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.5363. Min Act: -0.0000

Data Index: 1559503 (Python Code)

Max Activating Token Index: 430

Text #13

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.6849. Min Act: -0.0000

Data Index: 1398108 (Python Code)

Max Activating Token Index: 424

Text #14

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.6685. Min Act: -0.0000

Data Index: 1399560 (Python Code)

Max Activating Token Index: 531

Text #15

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.6282. Min Act: -0.0000

Data Index: 1578552 (Python Code)

Max Activating Token Index: 288

Text #16

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.6354. Min Act: -0.0000

Data Index: 1438610 (Python Code)

Max Activating Token Index: 826

Text #17

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.6425. Min Act: -0.0000

Data Index: 1585230 (Python Code)

Max Activating Token Index: 741

Text #18

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.6330. Min Act: -0.0000

Data Index: 1388296 (Python Code)

Max Activating Token Index: 147

Text #19

Max Range: 3.3484. Min Range: -3.3484

Max Act: 2.4894. Min Act: -0.0000

Data Index: 1624880 (Python Code)

Max Activating Token Index: 226