Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4487 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1626. Min Act: -0.1697
Data Index: 6909538 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 7891758 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 839556 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 2810192 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 820178 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 2295752 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 747112 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 2445300 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 2404977 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 2374642 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 2791738 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 203033 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 2893917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 569087 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 1092698 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 1890570 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 1715960 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1697
Data Index: 487654 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1313. Min Act: -0.1700
Data Index: 1627684 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1626. Min Range: -4.1626
Max Act: 4.1001. Min Act: -0.1700
Data Index: 400778 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19