Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1026. Min Range: -5.1026
Max Act: 5.1026. Min Act: -0.1700
Data Index: 797002 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1026. Min Range: -5.1026
Max Act: 5.0089. Min Act: -0.1700
Data Index: 2306427 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1026. Min Range: -5.1026
Max Act: 5.0089. Min Act: -0.1700
Data Index: 8553043 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1026. Min Range: -5.1026
Max Act: 5.0089. Min Act: -0.1700
Data Index: 7307085 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9776. Min Act: -0.1700
Data Index: 4666628 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9776. Min Act: -0.1700
Data Index: 30051 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9776. Min Act: -0.1700
Data Index: 7195583 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9464. Min Act: -0.1700
Data Index: 8387314 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9464. Min Act: -0.1700
Data Index: 956067 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9151. Min Act: -0.1700
Data Index: 8387312 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9151. Min Act: -0.1700
Data Index: 5454560 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9151. Min Act: -0.1700
Data Index: 2881925 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.9151. Min Act: -0.1700
Data Index: 8604268 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 7041069 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 3978768 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 6380712 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 1162887 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 3616676 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 45585 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1026. Min Range: -5.1026
Max Act: 4.8839. Min Act: -0.1700
Data Index: 4720976 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #19