Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3180 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0959. Min Act: -0.0003
Data Index: 1016438 (The Pile)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0962. Min Act: -0.0003
Data Index: 514369 (The Pile)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0963. Min Act: -0.0003
Data Index: 892745 (The Pile)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0949. Min Act: -0.0003
Data Index: 601546 (The Pile)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0946. Min Act: -0.0003
Data Index: 950334 (The Pile)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0997. Min Act: -0.0003
Data Index: 1518976 (The Pile)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0978. Min Act: -0.0003
Data Index: 1030588 (The Pile)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.1008. Min Act: -0.0003
Data Index: 1784890 (The Pile)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0872. Min Act: -0.0003
Data Index: 960114 (The Pile)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0821. Min Act: -0.0003
Data Index: 673542 (The Pile)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0912. Min Act: -0.0003
Data Index: 824717 (The Pile)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0945. Min Act: -0.0003
Data Index: 1101521 (The Pile)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0906. Min Act: -0.0003
Data Index: 43434 (The Pile)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0895. Min Act: -0.0003
Data Index: 455647 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0833. Min Act: -0.0003
Data Index: 692774 (The Pile)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0914. Min Act: -0.0003
Data Index: 1838694 (The Pile)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0941. Min Act: -0.0003
Data Index: 1724219 (The Pile)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0951. Min Act: -0.0003
Data Index: 1426703 (The Pile)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0881. Min Act: -0.0003
Data Index: 86319 (The Pile)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.1008. Min Range: -0.1008
Max Act: 0.0819. Min Act: -0.0003
Data Index: 625813 (The Pile)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #19