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

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

Neuron 2545 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3838. Min Range: -3.3838

Max Act: 3.3838. Min Act: -0.0000

Data Index: 1511048 (Python Code)

Max Activating Token Index: 50

Text #1

Max Range: 3.3838. Min Range: -3.3838

Max Act: 3.2271. Min Act: -0.0000

Data Index: 570786 (C4 (Web Text))

Max Activating Token Index: 169

Text #2

Max Range: 3.3838. Min Range: -3.3838

Max Act: 2.6969. Min Act: -0.0000

Data Index: 1408088 (Python Code)

Max Activating Token Index: 900

Text #3

Max Range: 3.3838. Min Range: -3.3838

Max Act: 2.3139. Min Act: -0.0000

Data Index: 1635118 (Python Code)

Max Activating Token Index: 579

Text #4

Max Range: 3.3838. Min Range: -3.3838

Max Act: 2.2379. Min Act: -0.0000

Data Index: 1164434 (C4 (Web Text))

Max Activating Token Index: 171

Text #5

Max Range: 3.3838. Min Range: -3.3838

Max Act: 2.2518. Min Act: -0.0000

Data Index: 1374436 (Python Code)

Max Activating Token Index: 841

Text #6

Max Range: 3.3838. Min Range: -3.3838

Max Act: 2.2219. Min Act: -0.0000

Data Index: 1637652 (Python Code)

Max Activating Token Index: 638

Text #7

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.9094. Min Act: -0.0000

Data Index: 1611133 (Python Code)

Max Activating Token Index: 810

Text #8

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.7898. Min Act: -0.0000

Data Index: 92891 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 3.3838. Min Range: -3.3838

Max Act: 2.0840. Min Act: -0.0000

Data Index: 1405957 (Python Code)

Max Activating Token Index: 388

Text #10

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.9146. Min Act: -0.0000

Data Index: 53353 (C4 (Web Text))

Max Activating Token Index: 683

Text #11

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.9896. Min Act: -0.0000

Data Index: 1308685 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.7718. Min Act: -0.0000

Data Index: 1631516 (Python Code)

Max Activating Token Index: 1001

Text #13

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.7807. Min Act: -0.0000

Data Index: 1385389 (Python Code)

Max Activating Token Index: 742

Text #14

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.8424. Min Act: -0.0000

Data Index: 1606514 (Python Code)

Max Activating Token Index: 302

Text #15

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.8273. Min Act: -0.0000

Data Index: 1501627 (Python Code)

Max Activating Token Index: 941

Text #16

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.8048. Min Act: -0.0000

Data Index: 1529142 (Python Code)

Max Activating Token Index: 94

Text #17

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.8131. Min Act: -0.0000

Data Index: 1373456 (Python Code)

Max Activating Token Index: 726

Text #18

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.7990. Min Act: -0.0000

Data Index: 1653830 (Python Code)

Max Activating Token Index: 669

Text #19

Max Range: 3.3838. Min Range: -3.3838

Max Act: 1.7997. Min Act: -0.0000

Data Index: 1612105 (Python Code)

Max Activating Token Index: 645