Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 5036 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0010. Min Act: -0.0002
Data Index: 176678 (C4 (Web Text))
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0009. Min Act: -0.0002
Data Index: 950742 (C4 (Web Text))
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0008. Min Act: -0.0002
Data Index: 1306349 (C4 (Web Text))
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0008. Min Act: -0.0002
Data Index: 1581642 (Python Code)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0001
Data Index: 503383 (C4 (Web Text))
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0001
Data Index: 1258084 (C4 (Web Text))
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 617947 (C4 (Web Text))
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 798667 (C4 (Web Text))
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 207344 (C4 (Web Text))
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 1644566 (Python Code)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 280600 (C4 (Web Text))
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 280081 (C4 (Web Text))
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 1271575 (C4 (Web Text))
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0001
Data Index: 824751 (C4 (Web Text))
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 1221963 (C4 (Web Text))
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 290580 (C4 (Web Text))
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 530346 (C4 (Web Text))
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 367860 (C4 (Web Text))
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 636951 (C4 (Web Text))
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0010. Min Range: -0.0010
Max Act: 0.0007. Min Act: -0.0002
Data Index: 650607 (C4 (Web Text))
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19