Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 323 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1145. Min Act: -0.0002

Data Index: 1511208 (Python Code)

Max Activating Token Index: 229

Text #1

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1053. Min Act: -0.0002

Data Index: 1635935 (Python Code)

Max Activating Token Index: 1005

Text #2

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1025. Min Act: -0.0002

Data Index: 1597715 (Python Code)

Max Activating Token Index: 96

Text #3

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.1031. Min Act: -0.0002

Data Index: 1510105 (Python Code)

Max Activating Token Index: 307

Text #4

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0956. Min Act: -0.0002

Data Index: 1476540 (Python Code)

Max Activating Token Index: 171

Text #5

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0979. Min Act: -0.0002

Data Index: 1602168 (Python Code)

Max Activating Token Index: 214

Text #6

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0928. Min Act: -0.0002

Data Index: 1392883 (Python Code)

Max Activating Token Index: 327

Text #7

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0934. Min Act: -0.0002

Data Index: 1542531 (Python Code)

Max Activating Token Index: 555

Text #8

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1587709 (Python Code)

Max Activating Token Index: 146

Text #9

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0931. Min Act: -0.0002

Data Index: 1421731 (Python Code)

Max Activating Token Index: 442

Text #10

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0940. Min Act: -0.0002

Data Index: 1493827 (Python Code)

Max Activating Token Index: 91

Text #11

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0835. Min Act: -0.0002

Data Index: 1498549 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0897. Min Act: -0.0002

Data Index: 1429097 (Python Code)

Max Activating Token Index: 253

Text #13

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1389456 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0891. Min Act: -0.0002

Data Index: 1385463 (Python Code)

Max Activating Token Index: 983

Text #15

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0929. Min Act: -0.0002

Data Index: 1425619 (Python Code)

Max Activating Token Index: 120

Text #16

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0865. Min Act: -0.0002

Data Index: 1569482 (Python Code)

Max Activating Token Index: 513

Text #17

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0875. Min Act: -0.0002

Data Index: 1493205 (Python Code)

Max Activating Token Index: 149

Text #18

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0874. Min Act: -0.0002

Data Index: 1492064 (Python Code)

Max Activating Token Index: 597

Text #19

Max Range: 0.1145. Min Range: -0.1145

Max Act: 0.0856. Min Act: -0.0002

Data Index: 1585525 (Python Code)

Max Activating Token Index: 901