Model: SoLU Model: 12 Layers, 6144 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3170 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')
Text #0
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0686. Min Act: -0.0001
Data Index: 455460 (C4 (Web Text))
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0708. Min Act: -0.0001
Data Index: 301024 (C4 (Web Text))
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0684. Min Act: -0.0001
Data Index: 670698 (C4 (Web Text))
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0776. Min Act: -0.0001
Data Index: 1416035 (Python Code)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0723. Min Act: -0.0001
Data Index: 1289276 (C4 (Web Text))
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0666. Min Act: -0.0001
Data Index: 1478089 (Python Code)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0698. Min Act: -0.0001
Data Index: 1652986 (Python Code)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0665. Min Act: -0.0001
Data Index: 1472165 (Python Code)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0651. Min Act: -0.0001
Data Index: 922209 (C4 (Web Text))
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0715. Min Act: -0.0001
Data Index: 203344 (C4 (Web Text))
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0595. Min Act: -0.0001
Data Index: 29138 (C4 (Web Text))
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0658. Min Act: -0.0001
Data Index: 742160 (C4 (Web Text))
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0614. Min Act: -0.0001
Data Index: 653280 (C4 (Web Text))
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0767. Min Act: -0.0001
Data Index: 815487 (C4 (Web Text))
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0634. Min Act: -0.0001
Data Index: 722303 (C4 (Web Text))
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0625. Min Act: -0.0001
Data Index: 1003583 (C4 (Web Text))
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0664. Min Act: -0.0001
Data Index: 1202520 (C4 (Web Text))
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0679. Min Act: -0.0001
Data Index: 1566191 (Python Code)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0618. Min Act: -0.0001
Data Index: 1453770 (Python Code)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0776. Min Range: -0.0776
Max Act: 0.0587. Min Act: -0.0001
Data Index: 314197 (C4 (Web Text))
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #19