Model: SoLU Model: 10 Layers, 5120 Neurons per Layer
Dataset: The Pile
Neuron 2670 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')
Text #0
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0064. Min Act: -0.0002
Data Index: 1027431 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0064. Min Act: -0.0002
Data Index: 1014708 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0064. Min Act: -0.0002
Data Index: 521394 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0062. Min Act: -0.0002
Data Index: 1145908 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 1208714 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 560588 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 347759 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 568288 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 1065902 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 377991 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 731704 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 539601 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 863634 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 1946819 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 971032 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 266334 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 815168 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0057. Min Act: -0.0002
Data Index: 1050904 (The Pile)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0055. Min Act: -0.0002
Data Index: 614437 (The Pile)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0064. Min Range: -0.0064
Max Act: 0.0052. Min Act: -0.0002
Data Index: 517845 (The Pile)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #19