Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 3484 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 2.2088. Min Range: -2.2088
Max Act: 2.2088. Min Act: -0.0001
Data Index: 1367640 (The Pile)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.9536. Min Act: -0.0001
Data Index: 302199 (The Pile)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 508583 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 453794 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 446473 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 1012267 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 579891 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 1118198 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 37175 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 1007715 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 1005443 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 1001967 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 1100543 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 884969 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 1195558 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 844376 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 826656 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 411442 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 742115 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2088. Min Range: -2.2088
Max Act: 1.8095. Min Act: -0.0001
Data Index: 96799 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19