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

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

Neuron 5166 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.2650. Min Act: -0.0001

Data Index: 1427506 (Python Code)

Max Activating Token Index: 221

Text #1

Max Range: 1.2650. Min Range: -1.2650

Max Act: 1.0172. Min Act: -0.0001

Data Index: 1603217 (Python Code)

Max Activating Token Index: 457

Text #2

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9966. Min Act: -0.0001

Data Index: 1625619 (Python Code)

Max Activating Token Index: 465

Text #3

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9220. Min Act: -0.0001

Data Index: 1648880 (Python Code)

Max Activating Token Index: 368

Text #4

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8899. Min Act: -0.0001

Data Index: 1558917 (Python Code)

Max Activating Token Index: 407

Text #5

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8837. Min Act: -0.0001

Data Index: 1499518 (Python Code)

Max Activating Token Index: 576

Text #6

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1485945 (Python Code)

Max Activating Token Index: 103

Text #7

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8611. Min Act: -0.0001

Data Index: 1466794 (Python Code)

Max Activating Token Index: 535

Text #8

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8198. Min Act: -0.0001

Data Index: 1637260 (Python Code)

Max Activating Token Index: 441

Text #9

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8134. Min Act: -0.0001

Data Index: 1488279 (Python Code)

Max Activating Token Index: 772

Text #10

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8871. Min Act: -0.0001

Data Index: 1457075 (Python Code)

Max Activating Token Index: 621

Text #11

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.9079. Min Act: -0.0001

Data Index: 1364424 (Python Code)

Max Activating Token Index: 102

Text #12

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8279. Min Act: -0.0001

Data Index: 1486300 (Python Code)

Max Activating Token Index: 728

Text #13

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8751. Min Act: -0.0001

Data Index: 1474948 (Python Code)

Max Activating Token Index: 923

Text #14

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8152. Min Act: -0.0001

Data Index: 1563281 (Python Code)

Max Activating Token Index: 762

Text #15

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8485. Min Act: -0.0001

Data Index: 1470379 (Python Code)

Max Activating Token Index: 383

Text #16

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8397. Min Act: -0.0001

Data Index: 1482539 (Python Code)

Max Activating Token Index: 151

Text #17

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8187. Min Act: -0.0001

Data Index: 1369356 (Python Code)

Max Activating Token Index: 783

Text #18

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.7809. Min Act: -0.0001

Data Index: 1596691 (Python Code)

Max Activating Token Index: 69

Text #19

Max Range: 1.2650. Min Range: -1.2650

Max Act: 0.8011. Min Act: -0.0001

Data Index: 1619078 (Python Code)

Max Activating Token Index: 574