Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: 80% C4 (Web Text) and 20% Python Code
Neuron 3949 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')
Text #0
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.6586. Min Act: -0.0001
Data Index: 525782 (C4 (Web Text))
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.7006. Min Act: -0.0001
Data Index: 1310042 (C4 (Web Text))
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.6843. Min Act: -0.0001
Data Index: 1144414 (C4 (Web Text))
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.5858. Min Act: -0.0001
Data Index: 1117671 (C4 (Web Text))
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.6370. Min Act: -0.0001
Data Index: 341014 (C4 (Web Text))
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4900. Min Act: -0.0001
Data Index: 1168035 (C4 (Web Text))
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.5403. Min Act: -0.0001
Data Index: 903759 (C4 (Web Text))
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.6120. Min Act: -0.0001
Data Index: 158448 (C4 (Web Text))
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4416. Min Act: -0.0001
Data Index: 203004 (C4 (Web Text))
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4965. Min Act: -0.0001
Data Index: 1267584 (C4 (Web Text))
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4907. Min Act: -0.0001
Data Index: 85653 (C4 (Web Text))
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4061. Min Act: -0.0001
Data Index: 291900 (C4 (Web Text))
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4805. Min Act: -0.0001
Data Index: 7144 (C4 (Web Text))
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.5664. Min Act: -0.0001
Data Index: 1082857 (C4 (Web Text))
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.5561. Min Act: -0.0001
Data Index: 851793 (C4 (Web Text))
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4836. Min Act: -0.0001
Data Index: 217097 (C4 (Web Text))
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.5197. Min Act: -0.0001
Data Index: 1137110 (C4 (Web Text))
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4615. Min Act: -0.0001
Data Index: 1162497 (C4 (Web Text))
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4614. Min Act: -0.0001
Data Index: 678283 (C4 (Web Text))
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7006. Min Range: -1.7006
Max Act: 1.4497. Min Act: -0.0001
Data Index: 1205712 (C4 (Web Text))
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19