Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3165 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.7685. Min Act: -0.1700
Data Index: 3428922 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.7060. Min Act: -0.1700
Data Index: 4008404 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.6435. Min Act: -0.1700
Data Index: 5500869 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.6435. Min Act: -0.1700
Data Index: 6659910 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.6435. Min Act: -0.1700
Data Index: 5931504 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.6122. Min Act: -0.1700
Data Index: 6164841 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.6122. Min Act: -0.1700
Data Index: 7659363 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.6122. Min Act: -0.1700
Data Index: 102531 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5810. Min Act: -0.1700
Data Index: 6589736 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5810. Min Act: -0.1700
Data Index: 2527951 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5810. Min Act: -0.1700
Data Index: 5032074 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5810. Min Act: -0.1700
Data Index: 6771035 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5497. Min Act: -0.1700
Data Index: 5575957 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5497. Min Act: -0.1700
Data Index: 4343928 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5810. Min Act: -0.1700
Data Index: 5975311 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5497. Min Act: -0.1700
Data Index: 2542890 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5185. Min Act: -0.1700
Data Index: 3373674 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5185. Min Act: -0.1700
Data Index: 3661570 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5185. Min Act: -0.1700
Data Index: 2139945 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7685. Min Range: -4.7685
Max Act: 4.5185. Min Act: -0.1700
Data Index: 2415341 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19