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

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

Neuron 3369 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.1824. Min Range: -7.1824

Max Act: 7.1824. Min Act: -0.0000

Data Index: 1513926 (Python Code)

Max Activating Token Index: 260

Text #1

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.9209. Min Act: -0.0000

Data Index: 1518796 (Python Code)

Max Activating Token Index: 638

Text #2

Max Range: 7.1824. Min Range: -7.1824

Max Act: 7.1190. Min Act: -0.0000

Data Index: 1490800 (Python Code)

Max Activating Token Index: 343

Text #3

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.8322. Min Act: -0.0000

Data Index: 1428093 (Python Code)

Max Activating Token Index: 746

Text #4

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.8613. Min Act: -0.0000

Data Index: 1655203 (Python Code)

Max Activating Token Index: 774

Text #5

Max Range: 7.1824. Min Range: -7.1824

Max Act: 7.0085. Min Act: -0.0000

Data Index: 1644776 (Python Code)

Max Activating Token Index: 854

Text #6

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.6622. Min Act: -0.0000

Data Index: 1459040 (Python Code)

Max Activating Token Index: 346

Text #7

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.8158. Min Act: -0.0000

Data Index: 1367955 (Python Code)

Max Activating Token Index: 487

Text #8

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.9577. Min Act: -0.0000

Data Index: 1530983 (Python Code)

Max Activating Token Index: 148

Text #9

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.9417. Min Act: -0.0000

Data Index: 1636152 (Python Code)

Max Activating Token Index: 721

Text #10

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.9365. Min Act: -0.0000

Data Index: 1400145 (Python Code)

Max Activating Token Index: 466

Text #11

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.9091. Min Act: -0.0000

Data Index: 1650606 (Python Code)

Max Activating Token Index: 961

Text #12

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.7067. Min Act: -0.0000

Data Index: 1373677 (Python Code)

Max Activating Token Index: 1008

Text #13

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.4751. Min Act: -0.0000

Data Index: 1362965 (Python Code)

Max Activating Token Index: 166

Text #14

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.5936. Min Act: -0.0000

Data Index: 1423219 (Python Code)

Max Activating Token Index: 617

Text #15

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.7352. Min Act: -0.0000

Data Index: 1433659 (Python Code)

Max Activating Token Index: 822

Text #16

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.3261. Min Act: -0.0000

Data Index: 1613673 (Python Code)

Max Activating Token Index: 834

Text #17

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.3263. Min Act: -0.0000

Data Index: 1527202 (Python Code)

Max Activating Token Index: 18

Text #18

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.5126. Min Act: -0.0000

Data Index: 1434346 (Python Code)

Max Activating Token Index: 195

Text #19

Max Range: 7.1824. Min Range: -7.1824

Max Act: 6.5045. Min Act: -0.0000

Data Index: 1449253 (Python Code)

Max Activating Token Index: 750