Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4246 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.4812. Min Act: -0.1700
Data Index: 603754 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.3874. Min Act: -0.1700
Data Index: 3312429 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.3249. Min Act: -0.1700
Data Index: 603757 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.2937. Min Act: -0.1700
Data Index: 6931257 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.2624. Min Act: -0.1700
Data Index: 4073500 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.2624. Min Act: -0.1700
Data Index: 5896922 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.1687. Min Act: -0.1700
Data Index: 198222 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.1374. Min Act: -0.1700
Data Index: 5037124 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.1687. Min Act: -0.1700
Data Index: 4346572 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.1062. Min Act: -0.1700
Data Index: 3048811 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0749. Min Act: -0.1700
Data Index: 6594714 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 4892883 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 776197 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 6378374 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 5645123 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 3341643 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 3558443 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 5412201 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 2886817 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4812. Min Range: -5.4812
Max Act: 5.0124. Min Act: -0.1700
Data Index: 961586 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19