Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3642 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.8561. Min Act: -0.1700
Data Index: 8177828 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.6371. Min Act: -0.1700
Data Index: 3390569 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.6214. Min Act: -0.1700
Data Index: 3742961 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.6058. Min Act: -0.1700
Data Index: 7084244 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5901. Min Act: -0.1700
Data Index: 1099898 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5901. Min Act: -0.1700
Data Index: 3112360 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.6058. Min Act: -0.1700
Data Index: 4166432 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5745. Min Act: -0.1700
Data Index: 6566564 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5745. Min Act: -0.1700
Data Index: 6372684 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5432. Min Act: -0.1700
Data Index: 98217 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5588. Min Act: -0.1700
Data Index: 110838 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5119. Min Act: -0.1700
Data Index: 1315061 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5432. Min Act: -0.1700
Data Index: 8097331 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.4962. Min Act: -0.1700
Data Index: 5999065 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.4962. Min Act: -0.1700
Data Index: 7403269 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.5119. Min Act: -0.1700
Data Index: 8764470 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.4962. Min Act: -0.1700
Data Index: 2313102 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.4962. Min Act: -0.1700
Data Index: 3529345 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.4962. Min Act: -0.1700
Data Index: 5947814 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8561. Min Range: -3.8561
Max Act: 3.4805. Min Act: -0.1700
Data Index: 1913836 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19