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

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

Neuron 2743 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.3330. Min Act: -0.0001

Data Index: 1568531 (Python Code)

Max Activating Token Index: 634

Text #1

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1635018 (Python Code)

Max Activating Token Index: 455

Text #2

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2155. Min Act: -0.0001

Data Index: 1656158 (Python Code)

Max Activating Token Index: 287

Text #3

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1943. Min Act: -0.0001

Data Index: 1527601 (Python Code)

Max Activating Token Index: 10

Text #4

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2008. Min Act: -0.0001

Data Index: 1381690 (Python Code)

Max Activating Token Index: 986

Text #5

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.2017. Min Act: -0.0001

Data Index: 517356 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1788. Min Act: -0.0001

Data Index: 1644859 (Python Code)

Max Activating Token Index: 51

Text #7

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1638. Min Act: -0.0001

Data Index: 1517080 (Python Code)

Max Activating Token Index: 975

Text #8

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1735. Min Act: -0.0001

Data Index: 1465585 (Python Code)

Max Activating Token Index: 881

Text #9

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1786. Min Act: -0.0001

Data Index: 1380299 (Python Code)

Max Activating Token Index: 31

Text #10

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1725. Min Act: -0.0001

Data Index: 1298595 (C4 (Web Text))

Max Activating Token Index: 498

Text #11

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1717. Min Act: -0.0001

Data Index: 243255 (C4 (Web Text))

Max Activating Token Index: 212

Text #12

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1775. Min Act: -0.0001

Data Index: 1437576 (Python Code)

Max Activating Token Index: 979

Text #13

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1643. Min Act: -0.0001

Data Index: 1476253 (Python Code)

Max Activating Token Index: 149

Text #14

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1670. Min Act: -0.0001

Data Index: 1573976 (Python Code)

Max Activating Token Index: 336

Text #15

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1648. Min Act: -0.0001

Data Index: 1587923 (Python Code)

Max Activating Token Index: 873

Text #16

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1640463 (Python Code)

Max Activating Token Index: 18

Text #17

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1520. Min Act: -0.0001

Data Index: 1486474 (Python Code)

Max Activating Token Index: 300

Text #18

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1522446 (Python Code)

Max Activating Token Index: 518

Text #19

Max Range: 0.3330. Min Range: -0.3330

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1516250 (Python Code)

Max Activating Token Index: 749