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

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

Neuron 3142 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: 2.0932. Min Range: -2.0932

Max Act: 2.0932. Min Act: 0.0000

Data Index: 1401448 (Python Code)

Max Activating Token Index: 136

Text #1

Max Range: 2.0932. Min Range: -2.0932

Max Act: 2.0673. Min Act: 0.0001

Data Index: 1505358 (Python Code)

Max Activating Token Index: 29

Text #2

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.8072. Min Act: 0.0000

Data Index: 1583778 (Python Code)

Max Activating Token Index: 30

Text #3

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.8281. Min Act: 0.0000

Data Index: 1364235 (Python Code)

Max Activating Token Index: 62

Text #4

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.8167. Min Act: 0.0001

Data Index: 1639112 (Python Code)

Max Activating Token Index: 26

Text #5

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.7659. Min Act: 0.0000

Data Index: 1532337 (Python Code)

Max Activating Token Index: 325

Text #6

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.7156. Min Act: 0.0000

Data Index: 1646198 (Python Code)

Max Activating Token Index: 224

Text #7

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.6872. Min Act: 0.0001

Data Index: 1561532 (Python Code)

Max Activating Token Index: 296

Text #8

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.5972. Min Act: 0.0001

Data Index: 1536429 (Python Code)

Max Activating Token Index: 97

Text #9

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.4444. Min Act: -0.0000

Data Index: 1519013 (Python Code)

Max Activating Token Index: 70

Text #10

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.5360. Min Act: 0.0000

Data Index: 1572408 (Python Code)

Max Activating Token Index: 104

Text #11

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.3712. Min Act: -0.0000

Data Index: 1453577 (Python Code)

Max Activating Token Index: 863

Text #12

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.4079. Min Act: -0.0000

Data Index: 1586639 (Python Code)

Max Activating Token Index: 615

Text #13

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.3548. Min Act: -0.0000

Data Index: 1514525 (Python Code)

Max Activating Token Index: 957

Text #14

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.3127. Min Act: -0.0000

Data Index: 1524226 (Python Code)

Max Activating Token Index: 788

Text #15

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.3303. Min Act: 0.0000

Data Index: 1620005 (Python Code)

Max Activating Token Index: 60

Text #16

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.3878. Min Act: 0.0000

Data Index: 1534277 (Python Code)

Max Activating Token Index: 266

Text #17

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.2284. Min Act: 0.0000

Data Index: 1523182 (Python Code)

Max Activating Token Index: 25

Text #18

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.2116. Min Act: -0.0000

Data Index: 1641729 (Python Code)

Max Activating Token Index: 686

Text #19

Max Range: 2.0932. Min Range: -2.0932

Max Act: 1.3343. Min Act: 0.0001

Data Index: 1629253 (Python Code)

Max Activating Token Index: 84