Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2653 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.6300. Min Act: -0.0001

Data Index: 1646394 (Python Code)

Max Activating Token Index: 957

Text #1

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.3866. Min Act: 0.0001

Data Index: 1391946 (Python Code)

Max Activating Token Index: 277

Text #2

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.3338. Min Act: -0.0001

Data Index: 1555515 (Python Code)

Max Activating Token Index: 158

Text #3

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.3244. Min Act: -0.0000

Data Index: 788544 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.2634. Min Act: 0.0001

Data Index: 1588850 (Python Code)

Max Activating Token Index: 238

Text #5

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.2736. Min Act: 0.0000

Data Index: 1625103 (Python Code)

Max Activating Token Index: 558

Text #6

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1172. Min Act: -0.0000

Data Index: 1582086 (Python Code)

Max Activating Token Index: 744

Text #7

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1786. Min Act: -0.0001

Data Index: 1540844 (Python Code)

Max Activating Token Index: 272

Text #8

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0995. Min Act: 0.0000

Data Index: 1438752 (Python Code)

Max Activating Token Index: 134

Text #9

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0903. Min Act: -0.0001

Data Index: 1169352 (C4 (Web Text))

Max Activating Token Index: 940

Text #10

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0809. Min Act: -0.0000

Data Index: 1541399 (Python Code)

Max Activating Token Index: 64

Text #11

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.1131. Min Act: -0.0001

Data Index: 1535281 (Python Code)

Max Activating Token Index: 271

Text #12

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0742. Min Act: -0.0000

Data Index: 976909 (C4 (Web Text))

Max Activating Token Index: 47

Text #13

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0373. Min Act: -0.0001

Data Index: 1430570 (Python Code)

Max Activating Token Index: 564

Text #14

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0908. Min Act: -0.0001

Data Index: 1439711 (Python Code)

Max Activating Token Index: 226

Text #15

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0953. Min Act: -0.0001

Data Index: 1428932 (Python Code)

Max Activating Token Index: 97

Text #16

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0656. Min Act: -0.0001

Data Index: 1456841 (Python Code)

Max Activating Token Index: 137

Text #17

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0614. Min Act: -0.0001

Data Index: 1466133 (Python Code)

Max Activating Token Index: 614

Text #18

Max Range: 1.6300. Min Range: -1.6300

Max Act: 0.9651. Min Act: -0.0000

Data Index: 1420497 (Python Code)

Max Activating Token Index: 93

Text #19

Max Range: 1.6300. Min Range: -1.6300

Max Act: 1.0101. Min Act: 0.0000

Data Index: 1551012 (Python Code)

Max Activating Token Index: 300