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

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

Neuron 3077 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3796. Min Range: -2.3796

Max Act: 2.3796. Min Act: -0.0000

Data Index: 1646702 (Python Code)

Max Activating Token Index: 45

Text #1

Max Range: 2.3796. Min Range: -2.3796

Max Act: 2.1008. Min Act: -0.0000

Data Index: 1553688 (Python Code)

Max Activating Token Index: 711

Text #2

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.9201. Min Act: 0.0000

Data Index: 1639810 (Python Code)

Max Activating Token Index: 516

Text #3

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.9100. Min Act: -0.0000

Data Index: 1563983 (Python Code)

Max Activating Token Index: 377

Text #4

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.8911. Min Act: -0.0000

Data Index: 729248 (C4 (Web Text))

Max Activating Token Index: 191

Text #5

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.8432. Min Act: -0.0000

Data Index: 1446179 (Python Code)

Max Activating Token Index: 679

Text #6

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.8411. Min Act: -0.0000

Data Index: 1409326 (Python Code)

Max Activating Token Index: 877

Text #7

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.8353. Min Act: 0.0000

Data Index: 1491415 (Python Code)

Max Activating Token Index: 284

Text #8

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.8020. Min Act: -0.0000

Data Index: 1596112 (Python Code)

Max Activating Token Index: 48

Text #9

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.7827. Min Act: -0.0000

Data Index: 1550081 (Python Code)

Max Activating Token Index: 306

Text #10

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.8122. Min Act: -0.0000

Data Index: 1405502 (Python Code)

Max Activating Token Index: 740

Text #11

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.6113. Min Act: -0.0000

Data Index: 1399582 (Python Code)

Max Activating Token Index: 88

Text #12

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.5962. Min Act: -0.0000

Data Index: 1649286 (Python Code)

Max Activating Token Index: 690

Text #13

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.7875. Min Act: 0.0000

Data Index: 1415278 (Python Code)

Max Activating Token Index: 54

Text #14

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.6652. Min Act: 0.0000

Data Index: 1371783 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.6300. Min Act: 0.0000

Data Index: 1443018 (Python Code)

Max Activating Token Index: 55

Text #16

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.6017. Min Act: 0.0000

Data Index: 1420428 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.5916. Min Act: -0.0000

Data Index: 1540159 (Python Code)

Max Activating Token Index: 156

Text #18

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.5569. Min Act: -0.0000

Data Index: 1099698 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 2.3796. Min Range: -2.3796

Max Act: 1.6483. Min Act: -0.0000

Data Index: 1528067 (Python Code)

Max Activating Token Index: 246