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

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

Neuron 2444 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2502. Min Act: -0.0000

Data Index: 557042 (C4 (Web Text))

Max Activating Token Index: 485

Text #1

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2312. Min Act: -0.0000

Data Index: 138233 (C4 (Web Text))

Max Activating Token Index: 161

Text #2

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2395. Min Act: -0.0000

Data Index: 1035489 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2036. Min Act: -0.0000

Data Index: 401210 (C4 (Web Text))

Max Activating Token Index: 597

Text #4

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2035. Min Act: -0.0000

Data Index: 300263 (C4 (Web Text))

Max Activating Token Index: 529

Text #5

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.2118. Min Act: -0.0000

Data Index: 1023534 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1969. Min Act: -0.0000

Data Index: 997600 (C4 (Web Text))

Max Activating Token Index: 534

Text #7

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1930. Min Act: -0.0000

Data Index: 704178 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1784. Min Act: -0.0000

Data Index: 935189 (C4 (Web Text))

Max Activating Token Index: 557

Text #9

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1876. Min Act: -0.0000

Data Index: 999702 (C4 (Web Text))

Max Activating Token Index: 972

Text #10

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1721. Min Act: -0.0000

Data Index: 107662 (C4 (Web Text))

Max Activating Token Index: 350

Text #11

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1790. Min Act: -0.0000

Data Index: 1051005 (C4 (Web Text))

Max Activating Token Index: 660

Text #12

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1704. Min Act: -0.0000

Data Index: 783921 (C4 (Web Text))

Max Activating Token Index: 900

Text #13

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1721. Min Act: -0.0000

Data Index: 202918 (C4 (Web Text))

Max Activating Token Index: 54

Text #14

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1602. Min Act: -0.0000

Data Index: 105268 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1563. Min Act: -0.0000

Data Index: 180638 (C4 (Web Text))

Max Activating Token Index: 821

Text #16

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1709. Min Act: -0.0000

Data Index: 1023113 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1524. Min Act: -0.0000

Data Index: 281392 (C4 (Web Text))

Max Activating Token Index: 646

Text #18

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1541. Min Act: -0.0000

Data Index: 589354 (C4 (Web Text))

Max Activating Token Index: 444

Text #19

Max Range: 0.2502. Min Range: -0.2502

Max Act: 0.1375. Min Act: -0.0000

Data Index: 40024 (C4 (Web Text))

Max Activating Token Index: 635