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

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

Neuron 3326 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: 4.1738. Min Range: -4.1738

Max Act: 4.1738. Min Act: -0.0000

Data Index: 1409063 (Python Code)

Max Activating Token Index: 923

Text #1

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.9887. Min Act: -0.0000

Data Index: 1451989 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.8712. Min Act: -0.0000

Data Index: 1429066 (Python Code)

Max Activating Token Index: 349

Text #3

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.7127. Min Act: -0.0000

Data Index: 1390100 (Python Code)

Max Activating Token Index: 977

Text #4

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.9577. Min Act: -0.0000

Data Index: 1510596 (Python Code)

Max Activating Token Index: 900

Text #5

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.8529. Min Act: -0.0000

Data Index: 1516380 (Python Code)

Max Activating Token Index: 65

Text #6

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.7897. Min Act: -0.0000

Data Index: 1649637 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.7566. Min Act: -0.0000

Data Index: 1262669 (C4 (Web Text))

Max Activating Token Index: 365

Text #8

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.6389. Min Act: -0.0000

Data Index: 1540181 (Python Code)

Max Activating Token Index: 905

Text #9

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.4918. Min Act: -0.0000

Data Index: 1423495 (Python Code)

Max Activating Token Index: 794

Text #10

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.7782. Min Act: -0.0000

Data Index: 84098 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.6047. Min Act: 0.0000

Data Index: 1515449 (Python Code)

Max Activating Token Index: 760

Text #12

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.5908. Min Act: -0.0000

Data Index: 258820 (C4 (Web Text))

Max Activating Token Index: 787

Text #13

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.5520. Min Act: -0.0000

Data Index: 1429574 (Python Code)

Max Activating Token Index: 382

Text #14

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.5350. Min Act: -0.0000

Data Index: 1562665 (Python Code)

Max Activating Token Index: 492

Text #15

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.3528. Min Act: -0.0000

Data Index: 1507297 (Python Code)

Max Activating Token Index: 83

Text #16

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.4673. Min Act: -0.0000

Data Index: 1583142 (Python Code)

Max Activating Token Index: 517

Text #17

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.3602. Min Act: -0.0000

Data Index: 1526739 (Python Code)

Max Activating Token Index: 596

Text #18

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.3504. Min Act: -0.0000

Data Index: 1363855 (Python Code)

Max Activating Token Index: 200

Text #19

Max Range: 4.1738. Min Range: -4.1738

Max Act: 2.1933. Min Act: -0.0000

Data Index: 1622798 (Python Code)

Max Activating Token Index: 838