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

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

Neuron 1729 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9805. Min Act: -0.0000

Data Index: 1388640 (Python Code)

Max Activating Token Index: 660

Text #1

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8639. Min Act: -0.0001

Data Index: 1602483 (Python Code)

Max Activating Token Index: 866

Text #2

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.9052. Min Act: -0.0000

Data Index: 1438884 (Python Code)

Max Activating Token Index: 38

Text #3

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8266. Min Act: -0.0000

Data Index: 1433831 (Python Code)

Max Activating Token Index: 396

Text #4

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1523475 (Python Code)

Max Activating Token Index: 1015

Text #5

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7939. Min Act: -0.0000

Data Index: 1544247 (Python Code)

Max Activating Token Index: 531

Text #6

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7826. Min Act: -0.0000

Data Index: 1539830 (Python Code)

Max Activating Token Index: 99

Text #7

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.8033. Min Act: -0.0000

Data Index: 1488515 (Python Code)

Max Activating Token Index: 259

Text #8

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1503644 (Python Code)

Max Activating Token Index: 814

Text #9

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7956. Min Act: -0.0000

Data Index: 1434010 (Python Code)

Max Activating Token Index: 349

Text #10

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7334. Min Act: -0.0000

Data Index: 1638348 (Python Code)

Max Activating Token Index: 45

Text #11

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7485. Min Act: -0.0000

Data Index: 1379529 (Python Code)

Max Activating Token Index: 505

Text #12

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1538964 (Python Code)

Max Activating Token Index: 451

Text #13

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7423. Min Act: -0.0000

Data Index: 1579383 (Python Code)

Max Activating Token Index: 290

Text #14

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1510914 (Python Code)

Max Activating Token Index: 148

Text #15

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.6927. Min Act: -0.0000

Data Index: 1651109 (Python Code)

Max Activating Token Index: 67

Text #16

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1561403 (Python Code)

Max Activating Token Index: 1017

Text #17

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7289. Min Act: -0.0000

Data Index: 1619889 (Python Code)

Max Activating Token Index: 117

Text #18

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1482073 (Python Code)

Max Activating Token Index: 358

Text #19

Max Range: 0.9805. Min Range: -0.9805

Max Act: 0.7266. Min Act: -0.0000

Data Index: 1386260 (Python Code)

Max Activating Token Index: 547