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

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

Neuron 436 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9149. Min Range: -3.9149

Max Act: 3.9149. Min Act: -0.0000

Data Index: 1401141 (Python Code)

Max Activating Token Index: 16

Text #1

Max Range: 3.9149. Min Range: -3.9149

Max Act: 3.9149. Min Act: -0.0000

Data Index: 1596469 (Python Code)

Max Activating Token Index: 16

Text #2

Max Range: 3.9149. Min Range: -3.9149

Max Act: 3.7514. Min Act: -0.0000

Data Index: 1426575 (Python Code)

Max Activating Token Index: 17

Text #3

Max Range: 3.9149. Min Range: -3.9149

Max Act: 3.0652. Min Act: -0.0000

Data Index: 1375714 (Python Code)

Max Activating Token Index: 21

Text #4

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.8432. Min Act: -0.0000

Data Index: 1375261 (Python Code)

Max Activating Token Index: 22

Text #5

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.9203. Min Act: -0.0001

Data Index: 1495387 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.6782. Min Act: -0.0001

Data Index: 1508199 (Python Code)

Max Activating Token Index: 134

Text #7

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.8390. Min Act: -0.0001

Data Index: 1472771 (Python Code)

Max Activating Token Index: 329

Text #8

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.6767. Min Act: -0.0000

Data Index: 1654393 (Python Code)

Max Activating Token Index: 28

Text #9

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.5118. Min Act: -0.0000

Data Index: 1477616 (Python Code)

Max Activating Token Index: 28

Text #10

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.5660. Min Act: -0.0001

Data Index: 1365601 (Python Code)

Max Activating Token Index: 949

Text #11

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1489132 (Python Code)

Max Activating Token Index: 940

Text #12

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.6345. Min Act: -0.0001

Data Index: 1370470 (Python Code)

Max Activating Token Index: 90

Text #13

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.3735. Min Act: -0.0000

Data Index: 1631356 (Python Code)

Max Activating Token Index: 31

Text #14

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.3603. Min Act: -0.0000

Data Index: 1632138 (Python Code)

Max Activating Token Index: 29

Text #15

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.4606. Min Act: -0.0000

Data Index: 1409543 (Python Code)

Max Activating Token Index: 13

Text #16

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.3005. Min Act: -0.0000

Data Index: 1585179 (Python Code)

Max Activating Token Index: 817

Text #17

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.6085. Min Act: -0.0000

Data Index: 1392220 (Python Code)

Max Activating Token Index: 61

Text #18

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.2301. Min Act: -0.0001

Data Index: 1625148 (Python Code)

Max Activating Token Index: 918

Text #19

Max Range: 3.9149. Min Range: -3.9149

Max Act: 2.3446. Min Act: -0.0000

Data Index: 1414812 (Python Code)

Max Activating Token Index: 28