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

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

Neuron 3150 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.8686. Min Act: -0.0000

Data Index: 1454787 (Python Code)

Max Activating Token Index: 156

Text #1

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7184. Min Act: -0.0000

Data Index: 1435968 (Python Code)

Max Activating Token Index: 306

Text #2

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7848. Min Act: -0.0001

Data Index: 1372474 (Python Code)

Max Activating Token Index: 861

Text #3

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7295. Min Act: -0.0000

Data Index: 1518886 (Python Code)

Max Activating Token Index: 93

Text #4

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7801. Min Act: -0.0001

Data Index: 1495276 (Python Code)

Max Activating Token Index: 792

Text #5

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7565. Min Act: -0.0001

Data Index: 1549370 (Python Code)

Max Activating Token Index: 661

Text #6

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7568. Min Act: -0.0001

Data Index: 1394332 (Python Code)

Max Activating Token Index: 567

Text #7

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7259. Min Act: -0.0001

Data Index: 1431931 (Python Code)

Max Activating Token Index: 686

Text #8

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7237. Min Act: -0.0001

Data Index: 1481664 (Python Code)

Max Activating Token Index: 980

Text #9

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6995. Min Act: -0.0001

Data Index: 1557603 (Python Code)

Max Activating Token Index: 897

Text #10

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7300. Min Act: -0.0000

Data Index: 1521807 (Python Code)

Max Activating Token Index: 74

Text #11

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7121. Min Act: -0.0001

Data Index: 1424845 (Python Code)

Max Activating Token Index: 1008

Text #12

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6784. Min Act: -0.0001

Data Index: 1604815 (Python Code)

Max Activating Token Index: 526

Text #13

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6916. Min Act: -0.0001

Data Index: 1369663 (Python Code)

Max Activating Token Index: 354

Text #14

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.7158. Min Act: -0.0001

Data Index: 1385790 (Python Code)

Max Activating Token Index: 935

Text #15

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6678. Min Act: -0.0001

Data Index: 1410064 (Python Code)

Max Activating Token Index: 1012

Text #16

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1639895 (Python Code)

Max Activating Token Index: 291

Text #17

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6418. Min Act: -0.0000

Data Index: 1547071 (Python Code)

Max Activating Token Index: 62

Text #18

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6508. Min Act: -0.0001

Data Index: 1488603 (Python Code)

Max Activating Token Index: 612

Text #19

Max Range: 0.8686. Min Range: -0.8686

Max Act: 0.6626. Min Act: -0.0001

Data Index: 1431241 (Python Code)

Max Activating Token Index: 632