Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 1234 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0083. Min Act: -0.0001
Data Index: 1637576 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0074. Min Act: -0.0001
Data Index: 1025049 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0075. Min Act: -0.0001
Data Index: 231629 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0073. Min Act: -0.0001
Data Index: 205156 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0073. Min Act: -0.0001
Data Index: 1270507 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0069. Min Act: -0.0001
Data Index: 1809346 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0068. Min Act: -0.0001
Data Index: 1375147 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0068. Min Act: -0.0001
Data Index: 618091 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0068. Min Act: -0.0001
Data Index: 890897 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0067. Min Act: -0.0001
Data Index: 180871 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0068. Min Act: -0.0001
Data Index: 1495006 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0066. Min Act: -0.0001
Data Index: 1456130 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0066. Min Act: -0.0001
Data Index: 385414 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0065. Min Act: -0.0001
Data Index: 1258805 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0064. Min Act: -0.0001
Data Index: 125937 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0064. Min Act: -0.0001
Data Index: 1847464 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0064. Min Act: -0.0001
Data Index: 558021 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0064. Min Act: -0.0001
Data Index: 1800503 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0063. Min Act: -0.0001
Data Index: 1499823 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0083. Min Range: -0.0083
Max Act: 0.0060. Min Act: -0.0001
Data Index: 682702 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19