Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6065 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.8844. Min Act: -0.1700
Data Index: 4097337 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.8219. Min Act: -0.1700
Data Index: 5262123 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.7907. Min Act: -0.1700
Data Index: 2852936 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.7282. Min Act: -0.1700
Data Index: 8574836 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6969. Min Act: -0.1700
Data Index: 8350707 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6657. Min Act: -0.1700
Data Index: 3989054 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6657. Min Act: -0.1700
Data Index: 5493938 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6032. Min Act: -0.1700
Data Index: 6246025 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6032. Min Act: -0.1700
Data Index: 1847758 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6344. Min Act: -0.1700
Data Index: 5231506 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6032. Min Act: -0.1700
Data Index: 2007080 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6032. Min Act: -0.1700
Data Index: 7086336 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.6032. Min Act: -0.1700
Data Index: 2536579 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.5719. Min Act: -0.1700
Data Index: 6817334 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.5719. Min Act: -0.1700
Data Index: 270786 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.5719. Min Act: -0.1700
Data Index: 8487606 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.5719. Min Act: -0.1700
Data Index: 6580797 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.5719. Min Act: -0.1700
Data Index: 5322553 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.5719. Min Act: -0.1700
Data Index: 3496544 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8844. Min Range: -5.8844
Max Act: 5.5407. Min Act: -0.1700
Data Index: 6115854 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #19