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

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

Neuron 1828 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.5761. Min Act: -0.0001

Data Index: 1445567 (Python Code)

Max Activating Token Index: 650

Text #1

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.5361. Min Act: -0.0001

Data Index: 1434627 (Python Code)

Max Activating Token Index: 204

Text #2

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.2391. Min Act: -0.0001

Data Index: 1549975 (Python Code)

Max Activating Token Index: 109

Text #3

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.2673. Min Act: -0.0001

Data Index: 1367020 (Python Code)

Max Activating Token Index: 610

Text #4

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.1181. Min Act: -0.0001

Data Index: 1546131 (Python Code)

Max Activating Token Index: 105

Text #5

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.1436. Min Act: -0.0001

Data Index: 1477866 (Python Code)

Max Activating Token Index: 18

Text #6

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9995. Min Act: -0.0001

Data Index: 1394646 (Python Code)

Max Activating Token Index: 482

Text #7

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0604. Min Act: -0.0001

Data Index: 1392263 (Python Code)

Max Activating Token Index: 796

Text #8

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9962. Min Act: -0.0001

Data Index: 1489797 (Python Code)

Max Activating Token Index: 177

Text #9

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9196. Min Act: -0.0001

Data Index: 991174 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0564. Min Act: -0.0001

Data Index: 1429833 (Python Code)

Max Activating Token Index: 46

Text #11

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9795. Min Act: -0.0001

Data Index: 1501543 (Python Code)

Max Activating Token Index: 285

Text #12

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9650. Min Act: -0.0001

Data Index: 1456294 (Python Code)

Max Activating Token Index: 688

Text #13

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9967. Min Act: -0.0001

Data Index: 1573497 (Python Code)

Max Activating Token Index: 238

Text #14

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0576. Min Act: -0.0001

Data Index: 1475245 (Python Code)

Max Activating Token Index: 534

Text #15

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.8930. Min Act: -0.0001

Data Index: 1640104 (Python Code)

Max Activating Token Index: 876

Text #16

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9848. Min Act: -0.0001

Data Index: 1547419 (Python Code)

Max Activating Token Index: 130

Text #17

Max Range: 1.5761. Min Range: -1.5761

Max Act: 1.0000. Min Act: -0.0001

Data Index: 1591309 (Python Code)

Max Activating Token Index: 232

Text #18

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.8790. Min Act: -0.0001

Data Index: 1571177 (Python Code)

Max Activating Token Index: 201

Text #19

Max Range: 1.5761. Min Range: -1.5761

Max Act: 0.9750. Min Act: -0.0001

Data Index: 1640978 (Python Code)

Max Activating Token Index: 749