Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3916 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0762. Min Act: -0.1700
Data Index: 1780857 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0450. Min Act: -0.1700
Data Index: 2272906 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0450. Min Act: -0.1700
Data Index: 2812409 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0450. Min Act: -0.1700
Data Index: 7972786 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0450. Min Act: -0.1700
Data Index: 5131681 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0762. Min Range: -4.0762
Max Act: 3.9824. Min Act: -0.1700
Data Index: 5022951 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0762. Min Range: -4.0762
Max Act: 3.9824. Min Act: -0.1700
Data Index: 5020679 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1700
Data Index: 2032859 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0762. Min Range: -4.0762
Max Act: 3.9824. Min Act: -0.1694
Data Index: 5181626 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0762. Min Range: -4.0762
Max Act: 3.9824. Min Act: -0.1698
Data Index: 5688332 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0762. Min Range: -4.0762
Max Act: 3.9824. Min Act: -0.1700
Data Index: 1953849 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0762. Min Range: -4.0762
Max Act: 3.9824. Min Act: -0.1700
Data Index: 5911637 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1700
Data Index: 6228493 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1700
Data Index: 6470553 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1700
Data Index: 1494529 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1700
Data Index: 3762317 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1700
Data Index: 1276452 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1700
Data Index: 6492497 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0762. Min Range: -4.0762
Max Act: 3.9824. Min Act: -0.1700
Data Index: 3715946 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0762. Min Range: -4.0762
Max Act: 4.0137. Min Act: -0.1697
Data Index: 756371 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19