Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1619 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.4611. Min Act: -0.0000

Data Index: 1492638 (Python Code)

Max Activating Token Index: 132

Text #1

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.4892. Min Act: -0.0000

Data Index: 1588273 (Python Code)

Max Activating Token Index: 537

Text #2

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.4534. Min Act: -0.0000

Data Index: 1387631 (Python Code)

Max Activating Token Index: 223

Text #3

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.3546. Min Act: -0.0000

Data Index: 1560757 (Python Code)

Max Activating Token Index: 157

Text #4

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.4643. Min Act: -0.0000

Data Index: 1523854 (Python Code)

Max Activating Token Index: 129

Text #5

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.4145. Min Act: -0.0000

Data Index: 1599637 (Python Code)

Max Activating Token Index: 555

Text #6

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.4771. Min Act: -0.0000

Data Index: 1474335 (Python Code)

Max Activating Token Index: 182

Text #7

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.3452. Min Act: -0.0000

Data Index: 1366469 (Python Code)

Max Activating Token Index: 357

Text #8

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.4785. Min Act: -0.0000

Data Index: 1506104 (Python Code)

Max Activating Token Index: 948

Text #9

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.3705. Min Act: -0.0000

Data Index: 1655340 (Python Code)

Max Activating Token Index: 54

Text #10

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1406006 (Python Code)

Max Activating Token Index: 228

Text #11

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.2226. Min Act: -0.0000

Data Index: 1601096 (Python Code)

Max Activating Token Index: 673

Text #12

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.2927. Min Act: -0.0000

Data Index: 1485602 (Python Code)

Max Activating Token Index: 410

Text #13

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.2578. Min Act: -0.0000

Data Index: 1570162 (Python Code)

Max Activating Token Index: 929

Text #14

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.1925. Min Act: -0.0000

Data Index: 1653399 (Python Code)

Max Activating Token Index: 993

Text #15

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.2399. Min Act: -0.0000

Data Index: 1582315 (Python Code)

Max Activating Token Index: 308

Text #16

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.2045. Min Act: -0.0001

Data Index: 1613702 (Python Code)

Max Activating Token Index: 608

Text #17

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.2431. Min Act: -0.0000

Data Index: 1654194 (Python Code)

Max Activating Token Index: 709

Text #18

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.0968. Min Act: -0.0000

Data Index: 1454680 (Python Code)

Max Activating Token Index: 771

Text #19

Max Range: 1.4892. Min Range: -1.4892

Max Act: 1.0864. Min Act: -0.0000

Data Index: 1633580 (Python Code)

Max Activating Token Index: 78