Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2478 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.3681. Min Act: -0.1700
Data Index: 3735678 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.3524. Min Act: -0.1700
Data Index: 640936 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.3524. Min Act: -0.1700
Data Index: 6191382 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.3524. Min Act: -0.1700
Data Index: 1412665 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.3367. Min Act: -0.1700
Data Index: 7176595 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.3053. Min Act: -0.1700
Data Index: 8576076 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.3053. Min Act: -0.1700
Data Index: 1842093 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2896. Min Act: -0.1700
Data Index: 6829636 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2739. Min Act: -0.1700
Data Index: 4221956 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2739. Min Act: -0.1700
Data Index: 5966476 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 166578 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 3369400 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 485371 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 5654069 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 5254195 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 2945617 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 7174961 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2582. Min Act: -0.1700
Data Index: 2180912 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2425. Min Act: -0.1700
Data Index: 2586593 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.3681. Min Range: -3.3681
Max Act: 3.2425. Min Act: -0.1700
Data Index: 1029389 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #19