Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1206 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.7731. Min Act: -0.0001

Data Index: 1610394 (Python Code)

Max Activating Token Index: 561

Text #1

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.7901. Min Act: -0.0001

Data Index: 1643658 (Python Code)

Max Activating Token Index: 377

Text #2

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.7134. Min Act: -0.0001

Data Index: 1415524 (Python Code)

Max Activating Token Index: 606

Text #3

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5638. Min Act: -0.0001

Data Index: 1614939 (Python Code)

Max Activating Token Index: 357

Text #4

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4519. Min Act: -0.0001

Data Index: 1645459 (Python Code)

Max Activating Token Index: 920

Text #5

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4972. Min Act: -0.0001

Data Index: 1576294 (Python Code)

Max Activating Token Index: 140

Text #6

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4368. Min Act: -0.0001

Data Index: 1497465 (Python Code)

Max Activating Token Index: 832

Text #7

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5068. Min Act: -0.0001

Data Index: 1392194 (Python Code)

Max Activating Token Index: 127

Text #8

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5045. Min Act: -0.0001

Data Index: 1636825 (Python Code)

Max Activating Token Index: 966

Text #9

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.5005. Min Act: -0.0001

Data Index: 1417809 (Python Code)

Max Activating Token Index: 22

Text #10

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.3865. Min Act: -0.0001

Data Index: 1578421 (Python Code)

Max Activating Token Index: 253

Text #11

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4711. Min Act: -0.0001

Data Index: 1545468 (Python Code)

Max Activating Token Index: 753

Text #12

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4662. Min Act: -0.0001

Data Index: 1591134 (Python Code)

Max Activating Token Index: 91

Text #13

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.3866. Min Act: -0.0001

Data Index: 1367221 (Python Code)

Max Activating Token Index: 555

Text #14

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4553. Min Act: -0.0001

Data Index: 1502991 (Python Code)

Max Activating Token Index: 345

Text #15

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4064. Min Act: -0.0001

Data Index: 1620385 (Python Code)

Max Activating Token Index: 64

Text #16

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4428. Min Act: -0.0001

Data Index: 1561011 (Python Code)

Max Activating Token Index: 933

Text #17

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4005. Min Act: -0.0001

Data Index: 1483869 (Python Code)

Max Activating Token Index: 191

Text #18

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4712. Min Act: -0.0001

Data Index: 1447555 (Python Code)

Max Activating Token Index: 262

Text #19

Max Range: 1.7901. Min Range: -1.7901

Max Act: 1.4189. Min Act: -0.0001

Data Index: 1404167 (Python Code)

Max Activating Token Index: 1008