Model: None
Dataset: The Pile
Neuron 2670 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')
Text #0
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.6300. Min Act: -0.1700
Data Index: 4555950 (The Pile)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.6300. Min Act: -0.1700
Data Index: 6410032 (The Pile)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.6144. Min Act: -0.1700
Data Index: 10500705 (The Pile)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.6144. Min Act: -0.1700
Data Index: 4340126 (The Pile)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5987. Min Act: -0.1700
Data Index: 7448133 (The Pile)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5831. Min Act: -0.1700
Data Index: 10413198 (The Pile)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5831. Min Act: -0.1700
Data Index: 1426999 (The Pile)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5674. Min Act: -0.1700
Data Index: 10174654 (The Pile)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5518. Min Act: -0.1700
Data Index: 5456057 (The Pile)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5518. Min Act: -0.1700
Data Index: 3360406 (The Pile)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5361. Min Act: -0.1700
Data Index: 3231504 (The Pile)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5361. Min Act: -0.1700
Data Index: 10407699 (The Pile)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5361. Min Act: -0.1700
Data Index: 3647902 (The Pile)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5204. Min Act: -0.1700
Data Index: 6065933 (The Pile)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5204. Min Act: -0.1700
Data Index: 38436 (The Pile)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5204. Min Act: -0.1700
Data Index: 1488077 (The Pile)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5048. Min Act: -0.1700
Data Index: 6853243 (The Pile)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5048. Min Act: -0.1700
Data Index: 1971092 (The Pile)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.5048. Min Act: -0.1700
Data Index: 7279085 (The Pile)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6300. Min Range: -3.6300
Max Act: 3.4891. Min Act: -0.1700
Data Index: 10133260 (The Pile)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19