Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4194 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.6159. Min Act: -0.1700
Data Index: 1619077 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.4909. Min Act: -0.1700
Data Index: 5132547 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.3347. Min Act: -0.1700
Data Index: 411450 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.3034. Min Act: -0.1700
Data Index: 7249551 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.2722. Min Act: -0.1700
Data Index: 7173771 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.2722. Min Act: -0.1700
Data Index: 102133 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.2409. Min Act: -0.1700
Data Index: 6833782 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.2097. Min Act: -0.1700
Data Index: 4677616 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.2097. Min Act: -0.1700
Data Index: 210082 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.2097. Min Act: -0.1700
Data Index: 5469438 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.2097. Min Act: -0.1700
Data Index: 8467215 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1784. Min Act: -0.1700
Data Index: 561713 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1784. Min Act: -0.1700
Data Index: 3591469 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1472. Min Act: -0.1700
Data Index: 5402278 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1472. Min Act: -0.1700
Data Index: 8487137 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1472. Min Act: -0.1700
Data Index: 2168712 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1472. Min Act: -0.1700
Data Index: 7511691 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1159. Min Act: -0.1700
Data Index: 2363921 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.0847. Min Act: -0.1700
Data Index: 5656906 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6159. Min Range: -6.6159
Max Act: 6.1159. Min Act: -0.1700
Data Index: 7585914 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #19