Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 258 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6745. Min Act: -0.0001

Data Index: 1475133 (Python Code)

Max Activating Token Index: 312

Text #1

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7303. Min Act: -0.0001

Data Index: 614203 (C4 (Web Text))

Max Activating Token Index: 516

Text #2

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6915. Min Act: -0.0001

Data Index: 1504653 (Python Code)

Max Activating Token Index: 583

Text #3

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6835. Min Act: -0.0001

Data Index: 1562052 (Python Code)

Max Activating Token Index: 367

Text #4

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5641. Min Act: -0.0001

Data Index: 1438645 (Python Code)

Max Activating Token Index: 697

Text #5

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6281. Min Act: -0.0001

Data Index: 1563250 (Python Code)

Max Activating Token Index: 824

Text #6

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5938. Min Act: -0.0001

Data Index: 1566085 (Python Code)

Max Activating Token Index: 278

Text #7

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6741. Min Act: -0.0001

Data Index: 1414223 (Python Code)

Max Activating Token Index: 661

Text #8

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6692. Min Act: -0.0001

Data Index: 1465282 (Python Code)

Max Activating Token Index: 939

Text #9

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6335. Min Act: -0.0001

Data Index: 1484679 (Python Code)

Max Activating Token Index: 994

Text #10

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5657. Min Act: -0.0001

Data Index: 1626031 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.7017. Min Act: -0.0001

Data Index: 1540320 (Python Code)

Max Activating Token Index: 773

Text #12

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6189. Min Act: -0.0001

Data Index: 492675 (C4 (Web Text))

Max Activating Token Index: 699

Text #13

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.6021. Min Act: -0.0001

Data Index: 882162 (C4 (Web Text))

Max Activating Token Index: 256

Text #14

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5709. Min Act: -0.0001

Data Index: 1471632 (Python Code)

Max Activating Token Index: 9

Text #15

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5326. Min Act: -0.0001

Data Index: 1460841 (Python Code)

Max Activating Token Index: 329

Text #16

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.4790. Min Act: -0.0001

Data Index: 1592630 (Python Code)

Max Activating Token Index: 737

Text #17

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5069. Min Act: -0.0001

Data Index: 1634716 (Python Code)

Max Activating Token Index: 493

Text #18

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5381. Min Act: -0.0001

Data Index: 1543228 (Python Code)

Max Activating Token Index: 449

Text #19

Max Range: 0.7303. Min Range: -0.7303

Max Act: 0.5128. Min Act: -0.0001

Data Index: 183942 (C4 (Web Text))

Max Activating Token Index: 402