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

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

Neuron 2713 in Layer 1

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: 1.5972. Min Range: -1.5972

Max Act: 1.5972. Min Act: -0.0002

Data Index: 60062 (C4 (Web Text))

Max Activating Token Index: 912

Text #1

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5967. Min Act: -0.0002

Data Index: 456086 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.5071. Min Act: -0.0002

Data Index: 451594 (C4 (Web Text))

Max Activating Token Index: 693

Text #3

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4565. Min Act: -0.0002

Data Index: 38776 (C4 (Web Text))

Max Activating Token Index: 312

Text #4

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4600. Min Act: -0.0002

Data Index: 808570 (C4 (Web Text))

Max Activating Token Index: 810

Text #5

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3809. Min Act: -0.0002

Data Index: 1031609 (C4 (Web Text))

Max Activating Token Index: 387

Text #6

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4168. Min Act: -0.0002

Data Index: 322461 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.4018. Min Act: -0.0002

Data Index: 1280897 (C4 (Web Text))

Max Activating Token Index: 283

Text #8

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3581. Min Act: -0.0002

Data Index: 825723 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3541. Min Act: -0.0002

Data Index: 167670 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3682. Min Act: -0.0002

Data Index: 574154 (C4 (Web Text))

Max Activating Token Index: 776

Text #11

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3727. Min Act: -0.0002

Data Index: 1102234 (C4 (Web Text))

Max Activating Token Index: 121

Text #12

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3781. Min Act: -0.0002

Data Index: 130821 (C4 (Web Text))

Max Activating Token Index: 29

Text #13

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3390. Min Act: -0.0002

Data Index: 936500 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3194. Min Act: -0.0002

Data Index: 873990 (C4 (Web Text))

Max Activating Token Index: 799

Text #15

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3046. Min Act: -0.0002

Data Index: 1147548 (C4 (Web Text))

Max Activating Token Index: 656

Text #16

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3026. Min Act: -0.0002

Data Index: 250028 (C4 (Web Text))

Max Activating Token Index: 651

Text #17

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.3243. Min Act: -0.0002

Data Index: 935801 (C4 (Web Text))

Max Activating Token Index: 945

Text #18

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2454. Min Act: -0.0002

Data Index: 369541 (C4 (Web Text))

Max Activating Token Index: 840

Text #19

Max Range: 1.5972. Min Range: -1.5972

Max Act: 1.2841. Min Act: -0.0002

Data Index: 210829 (C4 (Web Text))

Max Activating Token Index: 13