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

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

Neuron 4924 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.7374. Min Act: -0.0001

Data Index: 1594476 (Python Code)

Max Activating Token Index: 111

Text #1

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.5002. Min Act: -0.0001

Data Index: 1405484 (Python Code)

Max Activating Token Index: 120

Text #2

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.4828. Min Act: -0.0000

Data Index: 1360263 (Python Code)

Max Activating Token Index: 169

Text #3

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.7132. Min Act: -0.0000

Data Index: 1655493 (Python Code)

Max Activating Token Index: 158

Text #4

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3916. Min Act: -0.0001

Data Index: 1559198 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3328. Min Act: -0.0000

Data Index: 1522831 (Python Code)

Max Activating Token Index: 776

Text #6

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3174. Min Act: -0.0000

Data Index: 1641183 (Python Code)

Max Activating Token Index: 79

Text #7

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.3101. Min Act: -0.0001

Data Index: 1460896 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2590. Min Act: -0.0001

Data Index: 1445215 (Python Code)

Max Activating Token Index: 85

Text #9

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2124. Min Act: -0.0001

Data Index: 1546029 (Python Code)

Max Activating Token Index: 876

Text #10

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.2432. Min Act: -0.0001

Data Index: 1385687 (Python Code)

Max Activating Token Index: 263

Text #11

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.1251. Min Act: -0.0000

Data Index: 1419894 (Python Code)

Max Activating Token Index: 91

Text #12

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.1858. Min Act: -0.0000

Data Index: 1546240 (Python Code)

Max Activating Token Index: 113

Text #13

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.1832. Min Act: -0.0000

Data Index: 1511640 (Python Code)

Max Activating Token Index: 177

Text #14

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.0728. Min Act: -0.0001

Data Index: 1367975 (Python Code)

Max Activating Token Index: 600

Text #15

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.1180. Min Act: -0.0001

Data Index: 1368365 (Python Code)

Max Activating Token Index: 302

Text #16

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.1202. Min Act: -0.0001

Data Index: 1477242 (Python Code)

Max Activating Token Index: 191

Text #17

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.0765. Min Act: -0.0000

Data Index: 1651135 (Python Code)

Max Activating Token Index: 213

Text #18

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.0837. Min Act: -0.0000

Data Index: 1425317 (Python Code)

Max Activating Token Index: 1009

Text #19

Max Range: 1.7374. Min Range: -1.7374

Max Act: 1.1504. Min Act: -0.0000

Data Index: 1462628 (Python Code)

Max Activating Token Index: 515