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

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

Neuron 3887 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.3087. Min Act: -0.0000

Data Index: 1484035 (Python Code)

Max Activating Token Index: 921

Text #1

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.3081. Min Act: -0.0000

Data Index: 1572577 (Python Code)

Max Activating Token Index: 97

Text #2

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.3114. Min Act: 0.0000

Data Index: 1523114 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2689. Min Act: -0.0000

Data Index: 1363039 (Python Code)

Max Activating Token Index: 943

Text #4

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2670. Min Act: -0.0000

Data Index: 1625576 (Python Code)

Max Activating Token Index: 239

Text #5

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2713. Min Act: -0.0000

Data Index: 1380435 (Python Code)

Max Activating Token Index: 439

Text #6

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2558. Min Act: -0.0001

Data Index: 1370683 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2695. Min Act: -0.0000

Data Index: 1617743 (Python Code)

Max Activating Token Index: 33

Text #8

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2661. Min Act: -0.0001

Data Index: 1438375 (Python Code)

Max Activating Token Index: 388

Text #9

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2550. Min Act: -0.0000

Data Index: 1536332 (Python Code)

Max Activating Token Index: 642

Text #10

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2642. Min Act: 0.0000

Data Index: 1612760 (Python Code)

Max Activating Token Index: 764

Text #11

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2568. Min Act: -0.0001

Data Index: 1637332 (Python Code)

Max Activating Token Index: 976

Text #12

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2575. Min Act: -0.0001

Data Index: 1631013 (Python Code)

Max Activating Token Index: 286

Text #13

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2664. Min Act: -0.0001

Data Index: 1464756 (Python Code)

Max Activating Token Index: 960

Text #14

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2563. Min Act: -0.0001

Data Index: 1576446 (Python Code)

Max Activating Token Index: 309

Text #15

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2323. Min Act: -0.0000

Data Index: 1559661 (Python Code)

Max Activating Token Index: 827

Text #16

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2353. Min Act: -0.0000

Data Index: 1634512 (Python Code)

Max Activating Token Index: 876

Text #17

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2453. Min Act: -0.0000

Data Index: 1436119 (Python Code)

Max Activating Token Index: 178

Text #18

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1482650 (Python Code)

Max Activating Token Index: 937

Text #19

Max Range: 0.3114. Min Range: -0.3114

Max Act: 0.2195. Min Act: -0.0000

Data Index: 1362594 (Python Code)

Max Activating Token Index: 620