Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 2686 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0074. Min Act: -0.0000
Data Index: 1362506 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0066. Min Act: -0.0000
Data Index: 1682445 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0066. Min Act: -0.0000
Data Index: 56265 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0064. Min Act: -0.0001
Data Index: 1314115 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0064. Min Act: -0.0000
Data Index: 1389288 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0064. Min Act: -0.0001
Data Index: 688774 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0063. Min Act: -0.0001
Data Index: 1001414 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0063. Min Act: -0.0000
Data Index: 842179 (The Pile)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0062. Min Act: -0.0000
Data Index: 593120 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0062. Min Act: -0.0000
Data Index: 948907 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0060. Min Act: -0.0000
Data Index: 1291597 (The Pile)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0060. Min Act: -0.0001
Data Index: 1965521 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0060. Min Act: -0.0000
Data Index: 921516 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0059. Min Act: -0.0000
Data Index: 274430 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0059. Min Act: -0.0001
Data Index: 328132 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0059. Min Act: -0.0000
Data Index: 410055 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0059. Min Act: -0.0000
Data Index: 15325 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0060. Min Act: -0.0000
Data Index: 628977 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0058. Min Act: -0.0000
Data Index: 1955568 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0074. Min Range: -0.0074
Max Act: 0.0058. Min Act: -0.0000
Data Index: 893373 (The Pile)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19