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

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

Neuron 724 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8531. Min Act: -0.0001

Data Index: 1410914 (Python Code)

Max Activating Token Index: 811

Text #1

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.9157. Min Act: -0.0001

Data Index: 1598456 (Python Code)

Max Activating Token Index: 163

Text #2

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8342. Min Act: -0.0001

Data Index: 1519493 (Python Code)

Max Activating Token Index: 137

Text #3

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.9294. Min Act: -0.0001

Data Index: 1634574 (Python Code)

Max Activating Token Index: 184

Text #4

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8250. Min Act: -0.0001

Data Index: 1646209 (Python Code)

Max Activating Token Index: 41

Text #5

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.9593. Min Act: -0.0001

Data Index: 1547788 (Python Code)

Max Activating Token Index: 681

Text #6

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.6825. Min Act: -0.0001

Data Index: 1462541 (Python Code)

Max Activating Token Index: 908

Text #7

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.9178. Min Act: -0.0001

Data Index: 1365424 (Python Code)

Max Activating Token Index: 119

Text #8

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8813. Min Act: -0.0001

Data Index: 1452946 (Python Code)

Max Activating Token Index: 36

Text #9

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.7747. Min Act: -0.0001

Data Index: 1472359 (Python Code)

Max Activating Token Index: 741

Text #10

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8292. Min Act: -0.0001

Data Index: 1576519 (Python Code)

Max Activating Token Index: 593

Text #11

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.7940. Min Act: -0.0001

Data Index: 1387078 (Python Code)

Max Activating Token Index: 327

Text #12

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.7327. Min Act: -0.0001

Data Index: 1467746 (Python Code)

Max Activating Token Index: 727

Text #13

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.7543. Min Act: -0.0001

Data Index: 1602525 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.7569. Min Act: -0.0001

Data Index: 1375173 (Python Code)

Max Activating Token Index: 871

Text #15

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8873. Min Act: -0.0001

Data Index: 1510552 (Python Code)

Max Activating Token Index: 104

Text #16

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8521. Min Act: -0.0001

Data Index: 1435967 (Python Code)

Max Activating Token Index: 511

Text #17

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.7919. Min Act: -0.0001

Data Index: 1482213 (Python Code)

Max Activating Token Index: 134

Text #18

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.7525. Min Act: -0.0001

Data Index: 1616031 (Python Code)

Max Activating Token Index: 703

Text #19

Max Range: 0.9593. Min Range: -0.9593

Max Act: 0.8281. Min Act: -0.0001

Data Index: 1503012 (Python Code)

Max Activating Token Index: 16