Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 2678 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.9658. Min Act: -0.0001
Data Index: 1498166 (Python Code)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.7748. Min Act: -0.0001
Data Index: 1380869 (Python Code)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.7782. Min Act: -0.0001
Data Index: 1510049 (Python Code)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.5754. Min Act: -0.0001
Data Index: 1639087 (Python Code)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6123. Min Act: -0.0001
Data Index: 941097 (C4 (Web Text))
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6977. Min Act: -0.0001
Data Index: 363420 (C4 (Web Text))
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.5702. Min Act: -0.0001
Data Index: 370831 (C4 (Web Text))
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.7561. Min Act: -0.0001
Data Index: 1438039 (Python Code)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6686. Min Act: -0.0001
Data Index: 1524738 (Python Code)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6522. Min Act: -0.0001
Data Index: 703635 (C4 (Web Text))
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6191. Min Act: -0.0001
Data Index: 222250 (C4 (Web Text))
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.4859. Min Act: -0.0001
Data Index: 1441690 (Python Code)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6017. Min Act: -0.0001
Data Index: 1376837 (Python Code)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.5963. Min Act: -0.0001
Data Index: 913508 (C4 (Web Text))
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6004. Min Act: -0.0001
Data Index: 753536 (C4 (Web Text))
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.4755. Min Act: -0.0001
Data Index: 1360456 (Python Code)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.6469. Min Act: -0.0001
Data Index: 1140462 (C4 (Web Text))
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.5744. Min Act: -0.0001
Data Index: 1054661 (C4 (Web Text))
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.3949. Min Act: -0.0001
Data Index: 1207552 (C4 (Web Text))
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9658. Min Range: -1.9658
Max Act: 1.5038. Min Act: -0.0001
Data Index: 38222 (C4 (Web Text))
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19