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

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

Neuron 3090 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: 1.2766. Min Range: -1.2766

Max Act: 1.2766. Min Act: -0.0002

Data Index: 42163 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2339. Min Act: -0.0002

Data Index: 1103962 (C4 (Web Text))

Max Activating Token Index: 25

Text #2

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2715. Min Act: -0.0003

Data Index: 280244 (C4 (Web Text))

Max Activating Token Index: 835

Text #3

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2370. Min Act: -0.0002

Data Index: 637865 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2218. Min Act: -0.0002

Data Index: 822610 (C4 (Web Text))

Max Activating Token Index: 763

Text #5

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.2171. Min Act: -0.0002

Data Index: 986244 (C4 (Web Text))

Max Activating Token Index: 237

Text #6

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1934. Min Act: -0.0002

Data Index: 938140 (C4 (Web Text))

Max Activating Token Index: 34

Text #7

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1992. Min Act: -0.0002

Data Index: 695025 (C4 (Web Text))

Max Activating Token Index: 19

Text #8

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1889. Min Act: -0.0002

Data Index: 262731 (C4 (Web Text))

Max Activating Token Index: 92

Text #9

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1762. Min Act: -0.0002

Data Index: 59786 (C4 (Web Text))

Max Activating Token Index: 25

Text #10

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1899. Min Act: -0.0002

Data Index: 1082320 (C4 (Web Text))

Max Activating Token Index: 109

Text #11

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1684. Min Act: -0.0002

Data Index: 882651 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1693. Min Act: -0.0002

Data Index: 314543 (C4 (Web Text))

Max Activating Token Index: 236

Text #13

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1683. Min Act: -0.0002

Data Index: 693131 (C4 (Web Text))

Max Activating Token Index: 702

Text #14

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1751. Min Act: -0.0002

Data Index: 1051006 (C4 (Web Text))

Max Activating Token Index: 114

Text #15

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1723. Min Act: -0.0002

Data Index: 827271 (C4 (Web Text))

Max Activating Token Index: 121

Text #16

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1760. Min Act: -0.0002

Data Index: 77996 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1729. Min Act: -0.0002

Data Index: 756153 (C4 (Web Text))

Max Activating Token Index: 11

Text #18

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1378. Min Act: -0.0002

Data Index: 1012565 (C4 (Web Text))

Max Activating Token Index: 15

Text #19

Max Range: 1.2766. Min Range: -1.2766

Max Act: 1.1478. Min Act: -0.0002

Data Index: 1014615 (C4 (Web Text))

Max Activating Token Index: 30