Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3775 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.1544. Min Act: -0.1700
Data Index: 3555140 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.1232. Min Act: -0.1700
Data Index: 3584500 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0919. Min Act: -0.1700
Data Index: 2505074 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0607. Min Act: -0.1700
Data Index: 6701121 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0294. Min Act: -0.1700
Data Index: 8382786 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1544. Min Range: -5.1544
Max Act: 5.0294. Min Act: -0.1700
Data Index: 6955847 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9669. Min Act: -0.1700
Data Index: 5689404 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.9669. Min Act: -0.1700
Data Index: 2777860 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.8732. Min Act: -0.1700
Data Index: 6350337 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.8732. Min Act: -0.1700
Data Index: 2723439 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.8419. Min Act: -0.1700
Data Index: 6237558 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.8419. Min Act: -0.1700
Data Index: 5143875 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 6446120 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 7953321 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 2527312 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 3826903 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 6292165 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 7012903 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 1852322 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1544. Min Range: -5.1544
Max Act: 4.7794. Min Act: -0.1700
Data Index: 7796814 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19