Model: SoLU Model: 8 Layers, 4096 Neurons per Layer
Dataset: The Pile
Neuron 3456 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')
Text #0
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0028. Min Act: -0.0001
Data Index: 1580814 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0028. Min Act: -0.0001
Data Index: 1997220 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0027. Min Act: -0.0001
Data Index: 694563 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0025. Min Act: -0.0001
Data Index: 335935 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0025. Min Act: -0.0001
Data Index: 759096 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0025. Min Act: -0.0001
Data Index: 195092 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0025. Min Act: -0.0001
Data Index: 655500 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0025. Min Act: -0.0001
Data Index: 1672773 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 463718 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 308694 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 1588539 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 1671494 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 199514 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 706012 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 718665 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 1312205 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 226418 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 1331705 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 141339 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.0028. Min Range: -0.0028
Max Act: 0.0024. Min Act: -0.0001
Data Index: 931879 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19