Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3431 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.9667. Min Act: -0.1700
Data Index: 7379404 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.9354. Min Act: -0.1700
Data Index: 1309049 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.9042. Min Act: -0.1700
Data Index: 4433909 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8729. Min Act: -0.1700
Data Index: 2657471 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8417. Min Act: -0.1700
Data Index: 734801 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8417. Min Act: -0.1700
Data Index: 24958 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8417. Min Act: -0.1700
Data Index: 6502863 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 8133186 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 4841924 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 1931126 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1698
Data Index: 5789730 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 3357034 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 4855320 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 4054183 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 2601733 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.8104. Min Act: -0.1700
Data Index: 1114881 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.7792. Min Act: -0.1700
Data Index: 2980959 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.7792. Min Act: -0.1700
Data Index: 2575738 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.7792. Min Act: -0.1700
Data Index: 1403834 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9667. Min Range: -4.9667
Max Act: 4.7792. Min Act: -0.1700
Data Index: 4274467 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19