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

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

Neuron 993 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: 0.6419. Min Range: -0.6419

Max Act: 0.6251. Min Act: -0.0001

Data Index: 1435812 (Python Code)

Max Activating Token Index: 863

Text #1

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6340. Min Act: -0.0001

Data Index: 1515300 (Python Code)

Max Activating Token Index: 556

Text #2

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6242. Min Act: -0.0001

Data Index: 1430066 (Python Code)

Max Activating Token Index: 625

Text #3

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5748. Min Act: -0.0001

Data Index: 1509367 (Python Code)

Max Activating Token Index: 83

Text #4

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5867. Min Act: -0.0001

Data Index: 1508047 (Python Code)

Max Activating Token Index: 996

Text #5

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5837. Min Act: -0.0001

Data Index: 1373891 (Python Code)

Max Activating Token Index: 399

Text #6

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5842. Min Act: -0.0001

Data Index: 1469768 (Python Code)

Max Activating Token Index: 438

Text #7

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.6419. Min Act: -0.0001

Data Index: 1616333 (Python Code)

Max Activating Token Index: 522

Text #8

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5570. Min Act: -0.0001

Data Index: 1486991 (Python Code)

Max Activating Token Index: 126

Text #9

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5560. Min Act: -0.0001

Data Index: 1487577 (Python Code)

Max Activating Token Index: 758

Text #10

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5957. Min Act: -0.0001

Data Index: 1400741 (Python Code)

Max Activating Token Index: 568

Text #11

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5435. Min Act: -0.0001

Data Index: 1392123 (Python Code)

Max Activating Token Index: 44

Text #12

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5948. Min Act: -0.0001

Data Index: 1432969 (Python Code)

Max Activating Token Index: 115

Text #13

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5484. Min Act: -0.0001

Data Index: 1627724 (Python Code)

Max Activating Token Index: 779

Text #14

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5565. Min Act: -0.0001

Data Index: 1449016 (Python Code)

Max Activating Token Index: 755

Text #15

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5254. Min Act: -0.0001

Data Index: 1634228 (Python Code)

Max Activating Token Index: 861

Text #16

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5568. Min Act: -0.0001

Data Index: 1570189 (Python Code)

Max Activating Token Index: 206

Text #17

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5730. Min Act: -0.0001

Data Index: 1407361 (Python Code)

Max Activating Token Index: 219

Text #18

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5390. Min Act: -0.0001

Data Index: 1628711 (Python Code)

Max Activating Token Index: 7

Text #19

Max Range: 0.6419. Min Range: -0.6419

Max Act: 0.5470. Min Act: -0.0001

Data Index: 1621173 (Python Code)

Max Activating Token Index: 566