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

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

Neuron 70 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: 2.3669. Min Range: -2.3669

Max Act: 2.1587. Min Act: -0.0000

Data Index: 1585374 (Python Code)

Max Activating Token Index: 495

Text #1

Max Range: 2.3669. Min Range: -2.3669

Max Act: 2.3669. Min Act: -0.0000

Data Index: 1470523 (Python Code)

Max Activating Token Index: 817

Text #2

Max Range: 2.3669. Min Range: -2.3669

Max Act: 2.1553. Min Act: -0.0000

Data Index: 1635203 (Python Code)

Max Activating Token Index: 721

Text #3

Max Range: 2.3669. Min Range: -2.3669

Max Act: 2.2065. Min Act: -0.0000

Data Index: 1406397 (Python Code)

Max Activating Token Index: 1016

Text #4

Max Range: 2.3669. Min Range: -2.3669

Max Act: 2.0710. Min Act: -0.0000

Data Index: 1401051 (Python Code)

Max Activating Token Index: 925

Text #5

Max Range: 2.3669. Min Range: -2.3669

Max Act: 2.0362. Min Act: -0.0000

Data Index: 1529555 (Python Code)

Max Activating Token Index: 813

Text #6

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.9626. Min Act: -0.0000

Data Index: 1500540 (Python Code)

Max Activating Token Index: 504

Text #7

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.8849. Min Act: -0.0000

Data Index: 1559556 (Python Code)

Max Activating Token Index: 920

Text #8

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.7892. Min Act: -0.0000

Data Index: 1471846 (Python Code)

Max Activating Token Index: 907

Text #9

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.9142. Min Act: -0.0000

Data Index: 1510321 (Python Code)

Max Activating Token Index: 775

Text #10

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.8441. Min Act: -0.0000

Data Index: 1395023 (Python Code)

Max Activating Token Index: 971

Text #11

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1485919 (Python Code)

Max Activating Token Index: 178

Text #12

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.8573. Min Act: -0.0000

Data Index: 1461313 (Python Code)

Max Activating Token Index: 145

Text #13

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.8057. Min Act: -0.0000

Data Index: 1461492 (Python Code)

Max Activating Token Index: 738

Text #14

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.7176. Min Act: -0.0000

Data Index: 1491809 (Python Code)

Max Activating Token Index: 363

Text #15

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.7988. Min Act: -0.0000

Data Index: 1442954 (Python Code)

Max Activating Token Index: 204

Text #16

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.5620. Min Act: -0.0000

Data Index: 1550667 (Python Code)

Max Activating Token Index: 909

Text #17

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.7357. Min Act: -0.0000

Data Index: 1619836 (Python Code)

Max Activating Token Index: 628

Text #18

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1459544 (Python Code)

Max Activating Token Index: 536

Text #19

Max Range: 2.3669. Min Range: -2.3669

Max Act: 1.7499. Min Act: -0.0000

Data Index: 1387584 (Python Code)

Max Activating Token Index: 487