Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 900 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9739. Min Act: -0.0004

Data Index: 508 (C4 (Web Text))

Max Activating Token Index: 130

Text #1

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9219. Min Act: -0.0004

Data Index: 625072 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.9210. Min Act: -0.0004

Data Index: 603444 (C4 (Web Text))

Max Activating Token Index: 67

Text #3

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8819. Min Act: -0.0004

Data Index: 786272 (C4 (Web Text))

Max Activating Token Index: 121

Text #4

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8568. Min Act: -0.0004

Data Index: 686515 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8569. Min Act: -0.0004

Data Index: 237896 (C4 (Web Text))

Max Activating Token Index: 130

Text #6

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8951. Min Act: -0.0004

Data Index: 564673 (C4 (Web Text))

Max Activating Token Index: 25

Text #7

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8295. Min Act: -0.0004

Data Index: 649887 (C4 (Web Text))

Max Activating Token Index: 69

Text #8

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7905. Min Act: -0.0004

Data Index: 1056840 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8634. Min Act: -0.0004

Data Index: 1206146 (C4 (Web Text))

Max Activating Token Index: 337

Text #10

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8051. Min Act: -0.0004

Data Index: 414188 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8296. Min Act: -0.0004

Data Index: 287270 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8528. Min Act: -0.0004

Data Index: 275215 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7421. Min Act: -0.0004

Data Index: 1096828 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7771. Min Act: -0.0004

Data Index: 42383 (C4 (Web Text))

Max Activating Token Index: 713

Text #15

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7293. Min Act: -0.0004

Data Index: 614627 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.8088. Min Act: -0.0004

Data Index: 948163 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7806. Min Act: -0.0004

Data Index: 337611 (C4 (Web Text))

Max Activating Token Index: 64

Text #18

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7833. Min Act: -0.0004

Data Index: 324702 (C4 (Web Text))

Max Activating Token Index: 48

Text #19

Max Range: 0.9739. Min Range: -0.9739

Max Act: 0.7800. Min Act: -0.0004

Data Index: 428009 (C4 (Web Text))

Max Activating Token Index: 114