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

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

Neuron 407 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1326. Min Range: -2.1326

Max Act: 2.0464. Min Act: -0.0000

Data Index: 1392515 (Python Code)

Max Activating Token Index: 11

Text #1

Max Range: 2.1326. Min Range: -2.1326

Max Act: 2.1326. Min Act: -0.0000

Data Index: 1382351 (Python Code)

Max Activating Token Index: 121

Text #2

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.7585. Min Act: -0.0000

Data Index: 1613083 (Python Code)

Max Activating Token Index: 177

Text #3

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.5459. Min Act: -0.0000

Data Index: 1646001 (Python Code)

Max Activating Token Index: 871

Text #4

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.5247. Min Act: -0.0000

Data Index: 1535571 (Python Code)

Max Activating Token Index: 263

Text #5

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.4922. Min Act: -0.0000

Data Index: 1461156 (Python Code)

Max Activating Token Index: 354

Text #6

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.5764. Min Act: -0.0000

Data Index: 1620702 (Python Code)

Max Activating Token Index: 555

Text #7

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.4751. Min Act: -0.0000

Data Index: 1497396 (Python Code)

Max Activating Token Index: 439

Text #8

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.5311. Min Act: -0.0000

Data Index: 1492055 (Python Code)

Max Activating Token Index: 280

Text #9

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1406531 (Python Code)

Max Activating Token Index: 215

Text #10

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.7009. Min Act: -0.0000

Data Index: 1412037 (Python Code)

Max Activating Token Index: 988

Text #11

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.4984. Min Act: -0.0000

Data Index: 1400221 (Python Code)

Max Activating Token Index: 103

Text #12

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.4996. Min Act: -0.0000

Data Index: 1548254 (Python Code)

Max Activating Token Index: 17

Text #13

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.4648. Min Act: -0.0000

Data Index: 1403516 (Python Code)

Max Activating Token Index: 608

Text #14

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.4266. Min Act: -0.0000

Data Index: 1587404 (Python Code)

Max Activating Token Index: 504

Text #15

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.3387. Min Act: -0.0000

Data Index: 1592629 (Python Code)

Max Activating Token Index: 595

Text #16

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.3961. Min Act: -0.0000

Data Index: 1427384 (Python Code)

Max Activating Token Index: 38

Text #17

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.3963. Min Act: -0.0000

Data Index: 1570753 (Python Code)

Max Activating Token Index: 217

Text #18

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.3659. Min Act: -0.0000

Data Index: 1555888 (Python Code)

Max Activating Token Index: 557

Text #19

Max Range: 2.1326. Min Range: -2.1326

Max Act: 1.2812. Min Act: -0.0000

Data Index: 1615209 (Python Code)

Max Activating Token Index: 1015