Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 678 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0922. Min Act: -0.0001
Data Index: 1742304 (The Pile)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0921. Min Act: -0.0001
Data Index: 1822826 (The Pile)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0909. Min Act: -0.0001
Data Index: 513633 (The Pile)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0828. Min Act: -0.0001
Data Index: 1717971 (The Pile)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0843. Min Act: -0.0001
Data Index: 35092 (The Pile)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0846. Min Act: -0.0001
Data Index: 639146 (The Pile)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0834. Min Act: -0.0001
Data Index: 1219149 (The Pile)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0806. Min Act: -0.0001
Data Index: 28064 (The Pile)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0765. Min Act: -0.0001
Data Index: 1753334 (The Pile)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0788. Min Act: -0.0001
Data Index: 1110071 (The Pile)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0896. Min Act: -0.0001
Data Index: 1374214 (The Pile)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0822. Min Act: -0.0001
Data Index: 972010 (The Pile)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0810. Min Act: -0.0001
Data Index: 803103 (The Pile)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0764. Min Act: -0.0001
Data Index: 1992380 (The Pile)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0793. Min Act: -0.0001
Data Index: 1480804 (The Pile)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0793. Min Act: -0.0001
Data Index: 1806669 (The Pile)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0779. Min Act: -0.0000
Data Index: 462616 (The Pile)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0777. Min Act: -0.0001
Data Index: 478901 (The Pile)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0730. Min Act: -0.0001
Data Index: 1882820 (The Pile)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0922. Min Range: -0.0922
Max Act: 0.0777. Min Act: -0.0001
Data Index: 447758 (The Pile)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #19