Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2380 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.3849. Min Act: -0.0000

Data Index: 1626775 (Python Code)

Max Activating Token Index: 10

Text #1

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0511. Min Act: -0.0001

Data Index: 1600347 (Python Code)

Max Activating Token Index: 644

Text #2

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.1958. Min Act: -0.0001

Data Index: 1422857 (Python Code)

Max Activating Token Index: 707

Text #3

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0510. Min Act: -0.0000

Data Index: 1497058 (Python Code)

Max Activating Token Index: 143

Text #4

Max Range: 2.3849. Min Range: -2.3849

Max Act: 2.0970. Min Act: -0.0001

Data Index: 1569022 (Python Code)

Max Activating Token Index: 56

Text #5

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.9017. Min Act: -0.0001

Data Index: 1543936 (Python Code)

Max Activating Token Index: 676

Text #6

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.8582. Min Act: -0.0000

Data Index: 1628658 (Python Code)

Max Activating Token Index: 152

Text #7

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.7382. Min Act: -0.0000

Data Index: 1400975 (Python Code)

Max Activating Token Index: 239

Text #8

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.7549. Min Act: -0.0001

Data Index: 1467950 (Python Code)

Max Activating Token Index: 29

Text #9

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.6364. Min Act: -0.0000

Data Index: 1376237 (Python Code)

Max Activating Token Index: 55

Text #10

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.7224. Min Act: -0.0000

Data Index: 972212 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.6912. Min Act: -0.0000

Data Index: 1402695 (Python Code)

Max Activating Token Index: 1010

Text #12

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.8103. Min Act: -0.0000

Data Index: 1581927 (Python Code)

Max Activating Token Index: 935

Text #13

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.7193. Min Act: -0.0000

Data Index: 1443490 (Python Code)

Max Activating Token Index: 39

Text #14

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.8191. Min Act: -0.0001

Data Index: 1513594 (Python Code)

Max Activating Token Index: 793

Text #15

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.7095. Min Act: -0.0000

Data Index: 1455303 (Python Code)

Max Activating Token Index: 996

Text #16

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.6999. Min Act: -0.0000

Data Index: 1619073 (Python Code)

Max Activating Token Index: 114

Text #17

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.6528. Min Act: -0.0000

Data Index: 1487312 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.7952. Min Act: -0.0000

Data Index: 1427200 (Python Code)

Max Activating Token Index: 232

Text #19

Max Range: 2.3849. Min Range: -2.3849

Max Act: 1.6914. Min Act: -0.0000

Data Index: 1422763 (Python Code)

Max Activating Token Index: 912