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

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

Neuron 967 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: 2.5132. Min Range: -2.5132

Max Act: 2.5132. Min Act: -0.0000

Data Index: 1366744 (Python Code)

Max Activating Token Index: 426

Text #1

Max Range: 2.5132. Min Range: -2.5132

Max Act: 2.3985. Min Act: -0.0000

Data Index: 1621703 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 2.5132. Min Range: -2.5132

Max Act: 2.2840. Min Act: -0.0000

Data Index: 1581186 (Python Code)

Max Activating Token Index: 756

Text #3

Max Range: 2.5132. Min Range: -2.5132

Max Act: 2.3137. Min Act: -0.0000

Data Index: 1369398 (Python Code)

Max Activating Token Index: 783

Text #4

Max Range: 2.5132. Min Range: -2.5132

Max Act: 2.3783. Min Act: -0.0000

Data Index: 1497347 (Python Code)

Max Activating Token Index: 363

Text #5

Max Range: 2.5132. Min Range: -2.5132

Max Act: 2.1780. Min Act: 0.0000

Data Index: 1446652 (Python Code)

Max Activating Token Index: 417

Text #6

Max Range: 2.5132. Min Range: -2.5132

Max Act: 2.0003. Min Act: -0.0000

Data Index: 1572434 (Python Code)

Max Activating Token Index: 328

Text #7

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.9891. Min Act: -0.0000

Data Index: 1437727 (Python Code)

Max Activating Token Index: 679

Text #8

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.7819. Min Act: -0.0000

Data Index: 1364417 (Python Code)

Max Activating Token Index: 180

Text #9

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.8212. Min Act: -0.0000

Data Index: 1621285 (Python Code)

Max Activating Token Index: 334

Text #10

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.8334. Min Act: -0.0000

Data Index: 1623451 (Python Code)

Max Activating Token Index: 516

Text #11

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.8148. Min Act: -0.0000

Data Index: 1540500 (Python Code)

Max Activating Token Index: 369

Text #12

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.6772. Min Act: -0.0000

Data Index: 1528452 (Python Code)

Max Activating Token Index: 254

Text #13

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.6708. Min Act: -0.0000

Data Index: 1631659 (Python Code)

Max Activating Token Index: 830

Text #14

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.7222. Min Act: -0.0000

Data Index: 1374867 (Python Code)

Max Activating Token Index: 463

Text #15

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.8076. Min Act: -0.0000

Data Index: 1413505 (Python Code)

Max Activating Token Index: 650

Text #16

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.6685. Min Act: -0.0000

Data Index: 1369930 (Python Code)

Max Activating Token Index: 576

Text #17

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.6407. Min Act: -0.0000

Data Index: 1586896 (Python Code)

Max Activating Token Index: 981

Text #18

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.5171. Min Act: -0.0000

Data Index: 1424383 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 2.5132. Min Range: -2.5132

Max Act: 1.5800. Min Act: -0.0000

Data Index: 1582080 (Python Code)

Max Activating Token Index: 261