Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3993 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.7807. Min Act: -0.1700
Data Index: 3687081 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.6245. Min Act: -0.1700
Data Index: 5957944 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.6245. Min Act: -0.1700
Data Index: 2043944 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4995. Min Act: -0.1700
Data Index: 3669711 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4995. Min Act: -0.1700
Data Index: 344611 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4995. Min Act: -0.1700
Data Index: 6969770 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4682. Min Act: -0.1700
Data Index: 1259472 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4370. Min Act: -0.1700
Data Index: 8127257 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4057. Min Act: -0.1700
Data Index: 5789069 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4057. Min Act: -0.1700
Data Index: 1173990 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4057. Min Act: -0.1700
Data Index: 6164568 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.4057. Min Act: -0.1700
Data Index: 5645426 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3432. Min Act: -0.1700
Data Index: 7944824 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3432. Min Act: -0.1700
Data Index: 1816002 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3432. Min Act: -0.1700
Data Index: 73322 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3120. Min Act: -0.1700
Data Index: 6772785 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3120. Min Act: -0.1700
Data Index: 7799855 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3120. Min Act: -0.1700
Data Index: 8549040 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3120. Min Act: -0.1700
Data Index: 406222 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7807. Min Range: -5.7807
Max Act: 5.3120. Min Act: -0.1700
Data Index: 4260722 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19