Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1990 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0998. Min Range: -5.0998
Max Act: 5.0998. Min Act: -0.1700
Data Index: 6030112 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.9436. Min Act: -0.1700
Data Index: 7044003 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7873. Min Act: -0.1700
Data Index: 2399496 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7248. Min Act: -0.1700
Data Index: 5393057 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.7248. Min Act: -0.1700
Data Index: 8531733 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6936. Min Act: -0.1700
Data Index: 1210005 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6936. Min Act: -0.1700
Data Index: 2048742 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6936. Min Act: -0.1700
Data Index: 38709 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6623. Min Act: -0.1700
Data Index: 3318307 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6623. Min Act: -0.1700
Data Index: 5364972 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6623. Min Act: -0.1700
Data Index: 386610 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6623. Min Act: -0.1700
Data Index: 423694 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6623. Min Act: -0.1700
Data Index: 1931091 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6311. Min Act: -0.1700
Data Index: 1629836 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6623. Min Act: -0.1700
Data Index: 6071294 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.6311. Min Act: -0.1700
Data Index: 93922 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.5998. Min Act: -0.1700
Data Index: 6464270 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.5998. Min Act: -0.1700
Data Index: 1810644 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.5998. Min Act: -0.1700
Data Index: 6391463 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0998. Min Range: -5.0998
Max Act: 4.5686. Min Act: -0.1700
Data Index: 5758138 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #19