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

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

Neuron 200 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: 0.0840. Min Range: -0.0840

Max Act: 0.0840. Min Act: -0.0002

Data Index: 1188430 (C4 (Web Text))

Max Activating Token Index: 235

Text #1

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0749. Min Act: -0.0002

Data Index: 880280 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0699. Min Act: -0.0002

Data Index: 1144628 (C4 (Web Text))

Max Activating Token Index: 219

Text #3

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0703. Min Act: -0.0002

Data Index: 130130 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0649. Min Act: -0.0002

Data Index: 494803 (C4 (Web Text))

Max Activating Token Index: 110

Text #5

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0657. Min Act: -0.0002

Data Index: 638497 (C4 (Web Text))

Max Activating Token Index: 466

Text #6

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0672. Min Act: -0.0002

Data Index: 346706 (C4 (Web Text))

Max Activating Token Index: 399

Text #7

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0634. Min Act: -0.0002

Data Index: 298411 (C4 (Web Text))

Max Activating Token Index: 994

Text #8

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0643. Min Act: -0.0002

Data Index: 785270 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0663. Min Act: -0.0002

Data Index: 626004 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0641. Min Act: -0.0002

Data Index: 1044823 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0655. Min Act: -0.0002

Data Index: 310759 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0672. Min Act: -0.0002

Data Index: 199161 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0653. Min Act: -0.0002

Data Index: 67405 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0640. Min Act: -0.0002

Data Index: 100536 (C4 (Web Text))

Max Activating Token Index: 300

Text #15

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0634. Min Act: -0.0002

Data Index: 1015415 (C4 (Web Text))

Max Activating Token Index: 285

Text #16

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0639. Min Act: -0.0002

Data Index: 53631 (C4 (Web Text))

Max Activating Token Index: 274

Text #17

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1241489 (C4 (Web Text))

Max Activating Token Index: 394

Text #18

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0612. Min Act: -0.0002

Data Index: 637404 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.0840. Min Range: -0.0840

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1328201 (C4 (Web Text))

Max Activating Token Index: 192