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

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

Neuron 2280 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.6743. Min Act: -0.0000

Data Index: 1621461 (Python Code)

Max Activating Token Index: 361

Text #1

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.8011. Min Act: -0.0000

Data Index: 1531644 (Python Code)

Max Activating Token Index: 461

Text #2

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.6536. Min Act: -0.0000

Data Index: 1437659 (Python Code)

Max Activating Token Index: 526

Text #3

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.7614. Min Act: -0.0000

Data Index: 1556653 (Python Code)

Max Activating Token Index: 795

Text #4

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.6376. Min Act: -0.0000

Data Index: 1614822 (Python Code)

Max Activating Token Index: 889

Text #5

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.3841. Min Act: -0.0000

Data Index: 1533258 (Python Code)

Max Activating Token Index: 1006

Text #6

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.4014. Min Act: -0.0000

Data Index: 1629878 (Python Code)

Max Activating Token Index: 966

Text #7

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.2577. Min Act: -0.0000

Data Index: 1520542 (Python Code)

Max Activating Token Index: 985

Text #8

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.3592. Min Act: -0.0000

Data Index: 1395439 (Python Code)

Max Activating Token Index: 624

Text #9

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.3694. Min Act: -0.0000

Data Index: 1496563 (Python Code)

Max Activating Token Index: 333

Text #10

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.1457. Min Act: -0.0000

Data Index: 1604618 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.1416. Min Act: -0.0000

Data Index: 1442346 (Python Code)

Max Activating Token Index: 1016

Text #12

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.2530. Min Act: -0.0000

Data Index: 663562 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.2395. Min Act: -0.0000

Data Index: 1632345 (Python Code)

Max Activating Token Index: 60

Text #14

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.2273. Min Act: -0.0000

Data Index: 1446970 (Python Code)

Max Activating Token Index: 63

Text #15

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.1905. Min Act: -0.0000

Data Index: 1539627 (Python Code)

Max Activating Token Index: 1008

Text #16

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.2932. Min Act: -0.0000

Data Index: 1551757 (Python Code)

Max Activating Token Index: 200

Text #17

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.1440. Min Act: -0.0000

Data Index: 1416461 (Python Code)

Max Activating Token Index: 75

Text #18

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.1284. Min Act: -0.0000

Data Index: 1489024 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 2.8011. Min Range: -2.8011

Max Act: 2.0968. Min Act: -0.0000

Data Index: 1656202 (Python Code)

Max Activating Token Index: 878