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

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

Neuron 5188 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0579. Min Range: -1.0579

Max Act: 1.0579. Min Act: -0.0000

Data Index: 1538576 (Python Code)

Max Activating Token Index: 475

Text #1

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.8873. Min Act: -0.0000

Data Index: 1409619 (Python Code)

Max Activating Token Index: 520

Text #2

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7763. Min Act: -0.0000

Data Index: 1471453 (Python Code)

Max Activating Token Index: 305

Text #3

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7698. Min Act: -0.0000

Data Index: 1541264 (Python Code)

Max Activating Token Index: 211

Text #4

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7552. Min Act: -0.0000

Data Index: 1589924 (Python Code)

Max Activating Token Index: 943

Text #5

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.8093. Min Act: -0.0000

Data Index: 1424369 (Python Code)

Max Activating Token Index: 98

Text #6

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1569346 (Python Code)

Max Activating Token Index: 392

Text #7

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1499563 (Python Code)

Max Activating Token Index: 419

Text #8

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.8087. Min Act: -0.0000

Data Index: 1591269 (Python Code)

Max Activating Token Index: 479

Text #9

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1446494 (Python Code)

Max Activating Token Index: 488

Text #10

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.5871. Min Act: -0.0000

Data Index: 1557505 (Python Code)

Max Activating Token Index: 969

Text #11

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.5382. Min Act: -0.0000

Data Index: 387732 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.5516. Min Act: -0.0000

Data Index: 1370306 (Python Code)

Max Activating Token Index: 916

Text #13

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.5180. Min Act: -0.0000

Data Index: 1426970 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.5070. Min Act: -0.0000

Data Index: 1416696 (Python Code)

Max Activating Token Index: 414

Text #15

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.4865. Min Act: -0.0000

Data Index: 1481779 (Python Code)

Max Activating Token Index: 420

Text #16

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1628976 (Python Code)

Max Activating Token Index: 795

Text #17

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.4414. Min Act: -0.0000

Data Index: 1373133 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.4033. Min Act: -0.0000

Data Index: 822575 (C4 (Web Text))

Max Activating Token Index: 1015

Text #19

Max Range: 1.0579. Min Range: -1.0579

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1604001 (Python Code)

Max Activating Token Index: 918