Model: SoLU Model: 4 Layers, 2048 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 865 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')
Text #0
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0081. Min Act: -0.0006
Data Index: 136660 (C4 (Web Text))
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0084. Min Act: -0.0006
Data Index: 431468 (C4 (Web Text))
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0087. Min Act: -0.0006
Data Index: 746786 (C4 (Web Text))
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0076. Min Act: -0.0006
Data Index: 1553201 (Python Code)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0078. Min Act: -0.0006
Data Index: 856674 (C4 (Web Text))
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0080. Min Act: -0.0006
Data Index: 1511356 (Python Code)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0083. Min Act: -0.0006
Data Index: 261490 (C4 (Web Text))
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0078. Min Act: -0.0006
Data Index: 628129 (C4 (Web Text))
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0075. Min Act: -0.0006
Data Index: 1005057 (C4 (Web Text))
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0075. Min Act: -0.0006
Data Index: 1487119 (Python Code)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0074. Min Act: -0.0006
Data Index: 1406644 (Python Code)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0076. Min Act: -0.0006
Data Index: 1533566 (Python Code)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0075. Min Act: -0.0006
Data Index: 198241 (C4 (Web Text))
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0072. Min Act: -0.0006
Data Index: 783384 (C4 (Web Text))
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0073. Min Act: -0.0005
Data Index: 1413511 (Python Code)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0074. Min Act: -0.0006
Data Index: 1610849 (Python Code)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0068. Min Act: -0.0005
Data Index: 1549150 (Python Code)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0075. Min Act: -0.0006
Data Index: 1578020 (Python Code)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0067. Min Act: -0.0006
Data Index: 1446605 (Python Code)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0087. Min Range: -0.0087
Max Act: 0.0071. Min Act: -0.0006
Data Index: 1457860 (Python Code)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19