Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2978 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.2847. Min Range: -2.2847

Max Act: 2.2847. Min Act: -0.0000

Data Index: 1396212 (Python Code)

Max Activating Token Index: 190

Text #1

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7426. Min Act: -0.0000

Data Index: 1628071 (Python Code)

Max Activating Token Index: 135

Text #2

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.7705. Min Act: -0.0000

Data Index: 1463172 (Python Code)

Max Activating Token Index: 474

Text #3

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8443. Min Act: -0.0000

Data Index: 1538012 (Python Code)

Max Activating Token Index: 664

Text #4

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.8201. Min Act: -0.0000

Data Index: 1582725 (Python Code)

Max Activating Token Index: 930

Text #5

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.5663. Min Act: -0.0000

Data Index: 1631713 (Python Code)

Max Activating Token Index: 97

Text #6

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6293. Min Act: -0.0000

Data Index: 1414574 (Python Code)

Max Activating Token Index: 853

Text #7

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6536. Min Act: -0.0000

Data Index: 1496744 (Python Code)

Max Activating Token Index: 70

Text #8

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6122. Min Act: -0.0000

Data Index: 1581346 (Python Code)

Max Activating Token Index: 921

Text #9

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6290. Min Act: -0.0000

Data Index: 1476266 (Python Code)

Max Activating Token Index: 678

Text #10

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6969. Min Act: -0.0000

Data Index: 1627355 (Python Code)

Max Activating Token Index: 555

Text #11

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.5051. Min Act: -0.0000

Data Index: 1515672 (Python Code)

Max Activating Token Index: 490

Text #12

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6597. Min Act: -0.0000

Data Index: 1577764 (Python Code)

Max Activating Token Index: 875

Text #13

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.5562. Min Act: -0.0000

Data Index: 1361534 (Python Code)

Max Activating Token Index: 95

Text #14

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.6219. Min Act: -0.0000

Data Index: 1518206 (Python Code)

Max Activating Token Index: 734

Text #15

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.4769. Min Act: -0.0000

Data Index: 1410388 (Python Code)

Max Activating Token Index: 462

Text #16

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.4408. Min Act: -0.0000

Data Index: 1414164 (Python Code)

Max Activating Token Index: 45

Text #17

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.4325. Min Act: -0.0000

Data Index: 1468348 (Python Code)

Max Activating Token Index: 132

Text #18

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.3271. Min Act: -0.0000

Data Index: 1647787 (Python Code)

Max Activating Token Index: 458

Text #19

Max Range: 2.2847. Min Range: -2.2847

Max Act: 1.3898. Min Act: -0.0000

Data Index: 1432611 (Python Code)

Max Activating Token Index: 278