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

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

Neuron 5121 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3907. Min Range: -2.3907

Max Act: 2.3907. Min Act: -0.0000

Data Index: 1478467 (Python Code)

Max Activating Token Index: 497

Text #1

Max Range: 2.3907. Min Range: -2.3907

Max Act: 2.0660. Min Act: -0.0000

Data Index: 1453395 (Python Code)

Max Activating Token Index: 793

Text #2

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.9053. Min Act: -0.0000

Data Index: 1469153 (Python Code)

Max Activating Token Index: 539

Text #3

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.9850. Min Act: -0.0000

Data Index: 1377804 (Python Code)

Max Activating Token Index: 713

Text #4

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1493281 (Python Code)

Max Activating Token Index: 257

Text #5

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.6842. Min Act: -0.0000

Data Index: 1416297 (Python Code)

Max Activating Token Index: 724

Text #6

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.6415. Min Act: -0.0000

Data Index: 1635413 (Python Code)

Max Activating Token Index: 179

Text #7

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.5529. Min Act: -0.0000

Data Index: 1148587 (C4 (Web Text))

Max Activating Token Index: 659

Text #8

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.6308. Min Act: -0.0000

Data Index: 746779 (C4 (Web Text))

Max Activating Token Index: 746

Text #9

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.5962. Min Act: -0.0000

Data Index: 289743 (C4 (Web Text))

Max Activating Token Index: 258

Text #10

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.5768. Min Act: -0.0000

Data Index: 1403607 (Python Code)

Max Activating Token Index: 785

Text #11

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.5680. Min Act: -0.0000

Data Index: 1391002 (Python Code)

Max Activating Token Index: 596

Text #12

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.5606. Min Act: -0.0000

Data Index: 1515786 (Python Code)

Max Activating Token Index: 362

Text #13

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.5541. Min Act: -0.0000

Data Index: 1537466 (Python Code)

Max Activating Token Index: 98

Text #14

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.4488. Min Act: -0.0000

Data Index: 827251 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.4386. Min Act: -0.0000

Data Index: 1369565 (Python Code)

Max Activating Token Index: 476

Text #16

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.4919. Min Act: -0.0000

Data Index: 1418472 (Python Code)

Max Activating Token Index: 760

Text #17

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.5224. Min Act: -0.0000

Data Index: 1440513 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.3515. Min Act: -0.0000

Data Index: 1411907 (Python Code)

Max Activating Token Index: 865

Text #19

Max Range: 2.3907. Min Range: -2.3907

Max Act: 1.4151. Min Act: -0.0000

Data Index: 1550760 (Python Code)

Max Activating Token Index: 413