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

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

Neuron 703 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.5309. Min Act: -0.0005

Data Index: 1416271 (Python Code)

Max Activating Token Index: 261

Text #1

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4430. Min Act: -0.0005

Data Index: 1548528 (Python Code)

Max Activating Token Index: 636

Text #2

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4230. Min Act: -0.0005

Data Index: 1363850 (Python Code)

Max Activating Token Index: 437

Text #3

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4345. Min Act: -0.0005

Data Index: 1646044 (Python Code)

Max Activating Token Index: 680

Text #4

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4318. Min Act: -0.0005

Data Index: 1500338 (Python Code)

Max Activating Token Index: 91

Text #5

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4007. Min Act: -0.0005

Data Index: 1566779 (Python Code)

Max Activating Token Index: 256

Text #6

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4113. Min Act: -0.0005

Data Index: 1630241 (Python Code)

Max Activating Token Index: 83

Text #7

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4078. Min Act: -0.0005

Data Index: 1485628 (Python Code)

Max Activating Token Index: 221

Text #8

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4058. Min Act: -0.0005

Data Index: 1430578 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4047. Min Act: -0.0005

Data Index: 1600901 (Python Code)

Max Activating Token Index: 837

Text #10

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4031. Min Act: -0.0005

Data Index: 1441392 (Python Code)

Max Activating Token Index: 377

Text #11

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4027. Min Act: -0.0005

Data Index: 1552683 (Python Code)

Max Activating Token Index: 732

Text #12

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.4033. Min Act: -0.0005

Data Index: 1649723 (Python Code)

Max Activating Token Index: 774

Text #13

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3729. Min Act: -0.0005

Data Index: 1559035 (Python Code)

Max Activating Token Index: 475

Text #14

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3854. Min Act: -0.0005

Data Index: 1411223 (Python Code)

Max Activating Token Index: 89

Text #15

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3968. Min Act: -0.0005

Data Index: 1380687 (Python Code)

Max Activating Token Index: 157

Text #16

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3815. Min Act: -0.0005

Data Index: 1524690 (Python Code)

Max Activating Token Index: 722

Text #17

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3827. Min Act: -0.0005

Data Index: 1392475 (Python Code)

Max Activating Token Index: 325

Text #18

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3663. Min Act: -0.0005

Data Index: 1530422 (Python Code)

Max Activating Token Index: 974

Text #19

Max Range: 0.5309. Min Range: -0.5309

Max Act: 0.3946. Min Act: -0.0005

Data Index: 1591334 (Python Code)

Max Activating Token Index: 21