Model: None
Dataset: The Pile
Neuron 2237 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 9.6091. Min Range: -9.6091
Max Act: 9.6091. Min Act: -0.1700
Data Index: 6631926 (The Pile)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6091. Min Range: -9.6091
Max Act: 7.3904. Min Act: -0.1700
Data Index: 2808986 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6091. Min Range: -9.6091
Max Act: 7.3591. Min Act: -0.1700
Data Index: 2080783 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6091. Min Range: -9.6091
Max Act: 7.1716. Min Act: -0.1700
Data Index: 2238386 (The Pile)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 5213079 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 7133241 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 2186693 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 4172939 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 1942232 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 3660867 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 6333510 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8904. Min Act: -0.1700
Data Index: 3009778 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.8591. Min Act: -0.1700
Data Index: 9885646 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.7654. Min Act: -0.1700
Data Index: 3540518 (The Pile)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.7654. Min Act: -0.1700
Data Index: 6094254 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.7654. Min Act: -0.1700
Data Index: 2604885 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.7654. Min Act: -0.1700
Data Index: 4496113 (The Pile)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.7654. Min Act: -0.1700
Data Index: 10779973 (The Pile)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.7341. Min Act: -0.1700
Data Index: 4483127 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6091. Min Range: -9.6091
Max Act: 6.7341. Min Act: -0.1700
Data Index: 601640 (The Pile)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19