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

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

Neuron 4228 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.3683. Min Act: -0.0001

Data Index: 1644455 (Python Code)

Max Activating Token Index: 117

Text #1

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.5284. Min Act: -0.0001

Data Index: 1563151 (Python Code)

Max Activating Token Index: 57

Text #2

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.1221. Min Act: -0.0001

Data Index: 1524946 (Python Code)

Max Activating Token Index: 595

Text #3

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.0111. Min Act: -0.0001

Data Index: 1610691 (Python Code)

Max Activating Token Index: 283

Text #4

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.1714. Min Act: -0.0001

Data Index: 1466141 (Python Code)

Max Activating Token Index: 177

Text #5

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.8518. Min Act: -0.0001

Data Index: 1572576 (Python Code)

Max Activating Token Index: 263

Text #6

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.7618. Min Act: -0.0001

Data Index: 1568757 (Python Code)

Max Activating Token Index: 127

Text #7

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.5725. Min Act: -0.0001

Data Index: 1630586 (Python Code)

Max Activating Token Index: 757

Text #8

Max Range: 3.5284. Min Range: -3.5284

Max Act: 3.1108. Min Act: -0.0001

Data Index: 1560253 (Python Code)

Max Activating Token Index: 273

Text #9

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.5124. Min Act: -0.0001

Data Index: 1562187 (Python Code)

Max Activating Token Index: 604

Text #10

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.6217. Min Act: -0.0001

Data Index: 1544188 (Python Code)

Max Activating Token Index: 32

Text #11

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.1303. Min Act: -0.0001

Data Index: 1567542 (Python Code)

Max Activating Token Index: 217

Text #12

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.3216. Min Act: -0.0001

Data Index: 1508963 (Python Code)

Max Activating Token Index: 276

Text #13

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.3468. Min Act: -0.0001

Data Index: 1375015 (Python Code)

Max Activating Token Index: 700

Text #14

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.2956. Min Act: -0.0001

Data Index: 1550379 (Python Code)

Max Activating Token Index: 672

Text #15

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.4260. Min Act: -0.0001

Data Index: 1400277 (Python Code)

Max Activating Token Index: 165

Text #16

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.2977. Min Act: -0.0001

Data Index: 1637083 (Python Code)

Max Activating Token Index: 718

Text #17

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.1962. Min Act: -0.0001

Data Index: 1406121 (Python Code)

Max Activating Token Index: 120

Text #18

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.1716. Min Act: -0.0001

Data Index: 1465630 (Python Code)

Max Activating Token Index: 530

Text #19

Max Range: 3.5284. Min Range: -3.5284

Max Act: 2.1592. Min Act: -0.0001

Data Index: 1521161 (Python Code)

Max Activating Token Index: 484