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

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

Neuron 4771 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.8321. Min Act: -0.0000

Data Index: 1512823 (Python Code)

Max Activating Token Index: 360

Text #1

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.6922. Min Act: -0.0000

Data Index: 1435050 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.6475. Min Act: -0.0000

Data Index: 1386905 (Python Code)

Max Activating Token Index: 458

Text #3

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.6512. Min Act: -0.0000

Data Index: 1611352 (Python Code)

Max Activating Token Index: 494

Text #4

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5733. Min Act: -0.0000

Data Index: 1386269 (Python Code)

Max Activating Token Index: 594

Text #5

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1527674 (Python Code)

Max Activating Token Index: 620

Text #6

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5326. Min Act: -0.0000

Data Index: 1513637 (Python Code)

Max Activating Token Index: 136

Text #7

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1472234 (Python Code)

Max Activating Token Index: 91

Text #8

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5127. Min Act: -0.0000

Data Index: 1370005 (Python Code)

Max Activating Token Index: 720

Text #9

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5284. Min Act: -0.0000

Data Index: 1597219 (Python Code)

Max Activating Token Index: 90

Text #10

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5003. Min Act: -0.0000

Data Index: 1454717 (Python Code)

Max Activating Token Index: 25

Text #11

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4989. Min Act: -0.0000

Data Index: 1606466 (Python Code)

Max Activating Token Index: 990

Text #12

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5110. Min Act: -0.0000

Data Index: 1427728 (Python Code)

Max Activating Token Index: 536

Text #13

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4821. Min Act: -0.0000

Data Index: 1489893 (Python Code)

Max Activating Token Index: 516

Text #14

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.5681. Min Act: -0.0000

Data Index: 1434567 (Python Code)

Max Activating Token Index: 848

Text #15

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4758. Min Act: -0.0000

Data Index: 1403123 (Python Code)

Max Activating Token Index: 904

Text #16

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1371609 (Python Code)

Max Activating Token Index: 14

Text #17

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4944. Min Act: -0.0000

Data Index: 1607550 (Python Code)

Max Activating Token Index: 970

Text #18

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4898. Min Act: -0.0000

Data Index: 1416838 (Python Code)

Max Activating Token Index: 17

Text #19

Max Range: 0.8321. Min Range: -0.8321

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1402459 (Python Code)

Max Activating Token Index: 660