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

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

Neuron 2676 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7825. Min Act: -0.0003

Data Index: 1609181 (Python Code)

Max Activating Token Index: 703

Text #1

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7735. Min Act: -0.0003

Data Index: 1610786 (Python Code)

Max Activating Token Index: 921

Text #2

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7495. Min Act: -0.0003

Data Index: 1492413 (Python Code)

Max Activating Token Index: 956

Text #3

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7694. Min Act: -0.0003

Data Index: 1553178 (Python Code)

Max Activating Token Index: 953

Text #4

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7384. Min Act: -0.0003

Data Index: 1619287 (Python Code)

Max Activating Token Index: 869

Text #5

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7383. Min Act: -0.0003

Data Index: 1609131 (Python Code)

Max Activating Token Index: 960

Text #6

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7357. Min Act: -0.0003

Data Index: 1616736 (Python Code)

Max Activating Token Index: 230

Text #7

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7762. Min Act: -0.0003

Data Index: 1513097 (Python Code)

Max Activating Token Index: 968

Text #8

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7473. Min Act: -0.0003

Data Index: 1598573 (Python Code)

Max Activating Token Index: 919

Text #9

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7486. Min Act: -0.0003

Data Index: 1654485 (Python Code)

Max Activating Token Index: 320

Text #10

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6653. Min Act: -0.0003

Data Index: 1596816 (Python Code)

Max Activating Token Index: 367

Text #11

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7367. Min Act: -0.0003

Data Index: 1511447 (Python Code)

Max Activating Token Index: 922

Text #12

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7381. Min Act: -0.0003

Data Index: 1370353 (Python Code)

Max Activating Token Index: 178

Text #13

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7304. Min Act: -0.0003

Data Index: 1546205 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7014. Min Act: -0.0003

Data Index: 1418536 (Python Code)

Max Activating Token Index: 183

Text #15

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6859. Min Act: -0.0003

Data Index: 1426102 (Python Code)

Max Activating Token Index: 289

Text #16

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7711. Min Act: -0.0003

Data Index: 1448591 (Python Code)

Max Activating Token Index: 564

Text #17

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.7187. Min Act: -0.0003

Data Index: 1594938 (Python Code)

Max Activating Token Index: 110

Text #18

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6971. Min Act: -0.0003

Data Index: 1556136 (Python Code)

Max Activating Token Index: 219

Text #19

Max Range: 0.7825. Min Range: -0.7825

Max Act: 0.6884. Min Act: -0.0003

Data Index: 1598736 (Python Code)

Max Activating Token Index: 319