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

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

Neuron 2829 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.9669. Min Act: -0.0000

Data Index: 1544964 (Python Code)

Max Activating Token Index: 192

Text #1

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8855. Min Act: -0.0000

Data Index: 1444556 (Python Code)

Max Activating Token Index: 607

Text #2

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1557297 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8252. Min Act: -0.0000

Data Index: 1384852 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8188. Min Act: -0.0000

Data Index: 1429488 (Python Code)

Max Activating Token Index: 546

Text #5

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8137. Min Act: -0.0000

Data Index: 1425610 (Python Code)

Max Activating Token Index: 536

Text #6

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8354. Min Act: -0.0000

Data Index: 1395879 (Python Code)

Max Activating Token Index: 355

Text #7

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1500160 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1466648 (Python Code)

Max Activating Token Index: 364

Text #9

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7372. Min Act: -0.0000

Data Index: 1655910 (Python Code)

Max Activating Token Index: 209

Text #10

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7553. Min Act: -0.0000

Data Index: 1371882 (Python Code)

Max Activating Token Index: 562

Text #11

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7103. Min Act: -0.0000

Data Index: 1500055 (Python Code)

Max Activating Token Index: 626

Text #12

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6913. Min Act: -0.0000

Data Index: 1601125 (Python Code)

Max Activating Token Index: 693

Text #13

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7259. Min Act: -0.0000

Data Index: 1424498 (Python Code)

Max Activating Token Index: 376

Text #14

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.7353. Min Act: -0.0000

Data Index: 1521074 (Python Code)

Max Activating Token Index: 256

Text #15

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6664. Min Act: -0.0000

Data Index: 1511817 (Python Code)

Max Activating Token Index: 516

Text #16

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6998. Min Act: -0.0000

Data Index: 1510389 (Python Code)

Max Activating Token Index: 418

Text #17

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1558089 (Python Code)

Max Activating Token Index: 383

Text #18

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6769. Min Act: -0.0000

Data Index: 1586796 (Python Code)

Max Activating Token Index: 335

Text #19

Max Range: 0.9669. Min Range: -0.9669

Max Act: 0.6675. Min Act: -0.0000

Data Index: 1631494 (Python Code)

Max Activating Token Index: 509