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

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

Neuron 4698 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.9516. Min Act: -0.0000

Data Index: 1610537 (Python Code)

Max Activating Token Index: 152

Text #1

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6737. Min Act: -0.0000

Data Index: 1540461 (Python Code)

Max Activating Token Index: 736

Text #2

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6976. Min Act: -0.0000

Data Index: 1483123 (Python Code)

Max Activating Token Index: 503

Text #3

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7160. Min Act: -0.0000

Data Index: 1647673 (Python Code)

Max Activating Token Index: 573

Text #4

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6787. Min Act: -0.0000

Data Index: 1404935 (Python Code)

Max Activating Token Index: 691

Text #5

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6336. Min Act: -0.0000

Data Index: 987628 (C4 (Web Text))

Max Activating Token Index: 300

Text #6

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1405491 (Python Code)

Max Activating Token Index: 923

Text #7

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.7735. Min Act: -0.0000

Data Index: 19751 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1367427 (Python Code)

Max Activating Token Index: 764

Text #9

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.6082. Min Act: -0.0000

Data Index: 274787 (C4 (Web Text))

Max Activating Token Index: 307

Text #10

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1496726 (Python Code)

Max Activating Token Index: 859

Text #11

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5396. Min Act: -0.0000

Data Index: 1401058 (Python Code)

Max Activating Token Index: 22

Text #12

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1465492 (Python Code)

Max Activating Token Index: 781

Text #13

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5151. Min Act: -0.0000

Data Index: 1474673 (Python Code)

Max Activating Token Index: 377

Text #14

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1456554 (Python Code)

Max Activating Token Index: 873

Text #15

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1516031 (Python Code)

Max Activating Token Index: 294

Text #16

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5619. Min Act: -0.0000

Data Index: 1379888 (Python Code)

Max Activating Token Index: 392

Text #17

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5144. Min Act: -0.0000

Data Index: 1353105 (C4 (Web Text))

Max Activating Token Index: 788

Text #18

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.4996. Min Act: -0.0000

Data Index: 1378345 (Python Code)

Max Activating Token Index: 312

Text #19

Max Range: 0.9516. Min Range: -0.9516

Max Act: 0.5089. Min Act: -0.0000

Data Index: 1470739 (Python Code)

Max Activating Token Index: 281