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

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

Neuron 4847 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.7302. Min Act: -0.0001

Data Index: 1552081 (Python Code)

Max Activating Token Index: 146

Text #1

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6945. Min Act: -0.0001

Data Index: 1622489 (Python Code)

Max Activating Token Index: 172

Text #2

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6368. Min Act: -0.0001

Data Index: 1507497 (Python Code)

Max Activating Token Index: 257

Text #3

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6522. Min Act: -0.0001

Data Index: 1537047 (Python Code)

Max Activating Token Index: 99

Text #4

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6189. Min Act: -0.0001

Data Index: 1406010 (Python Code)

Max Activating Token Index: 161

Text #5

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6162. Min Act: -0.0001

Data Index: 1366142 (Python Code)

Max Activating Token Index: 191

Text #6

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6018. Min Act: -0.0001

Data Index: 1580154 (Python Code)

Max Activating Token Index: 168

Text #7

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5964. Min Act: -0.0001

Data Index: 1583888 (Python Code)

Max Activating Token Index: 126

Text #8

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.6013. Min Act: -0.0001

Data Index: 1498066 (Python Code)

Max Activating Token Index: 92

Text #9

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5944. Min Act: -0.0001

Data Index: 1513923 (Python Code)

Max Activating Token Index: 193

Text #10

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5991. Min Act: -0.0001

Data Index: 1592072 (Python Code)

Max Activating Token Index: 70

Text #11

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5911. Min Act: -0.0001

Data Index: 1441318 (Python Code)

Max Activating Token Index: 147

Text #12

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5832. Min Act: -0.0001

Data Index: 1377561 (Python Code)

Max Activating Token Index: 228

Text #13

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5897. Min Act: -0.0001

Data Index: 1476605 (Python Code)

Max Activating Token Index: 197

Text #14

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5838. Min Act: -0.0001

Data Index: 1471052 (Python Code)

Max Activating Token Index: 105

Text #15

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5898. Min Act: -0.0001

Data Index: 1600312 (Python Code)

Max Activating Token Index: 194

Text #16

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5736. Min Act: -0.0001

Data Index: 1535614 (Python Code)

Max Activating Token Index: 249

Text #17

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5813. Min Act: -0.0001

Data Index: 1495926 (Python Code)

Max Activating Token Index: 233

Text #18

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5802. Min Act: -0.0001

Data Index: 1486955 (Python Code)

Max Activating Token Index: 111

Text #19

Max Range: 0.7302. Min Range: -0.7302

Max Act: 0.5747. Min Act: -0.0001

Data Index: 1449996 (Python Code)

Max Activating Token Index: 220