Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1325 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0859. Min Act: -0.0003

Data Index: 1537614 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1443584 (Python Code)

Max Activating Token Index: 1023

Text #2

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0644. Min Act: -0.0003

Data Index: 788574 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0579. Min Act: -0.0003

Data Index: 1210722 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0577. Min Act: -0.0004

Data Index: 587070 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0535. Min Act: -0.0003

Data Index: 1458353 (Python Code)

Max Activating Token Index: 1023

Text #6

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0553. Min Act: -0.0003

Data Index: 844451 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0537. Min Act: -0.0003

Data Index: 1098413 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0504. Min Act: -0.0003

Data Index: 1592462 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1493561 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0489. Min Act: -0.0003

Data Index: 447285 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0469. Min Act: -0.0003

Data Index: 9129 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0468. Min Act: -0.0003

Data Index: 878763 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0469. Min Act: -0.0003

Data Index: 341186 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0462. Min Act: -0.0003

Data Index: 441778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0458. Min Act: -0.0003

Data Index: 1365858 (Python Code)

Max Activating Token Index: 1023

Text #16

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0459. Min Act: -0.0003

Data Index: 1153478 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0451. Min Act: -0.0003

Data Index: 1410901 (Python Code)

Max Activating Token Index: 1023

Text #18

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0448. Min Act: -0.0003

Data Index: 127148 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0444. Min Act: -0.0003

Data Index: 633390 (C4 (Web Text))

Max Activating Token Index: 1023