Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2640 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.8007. Min Act: -0.1700
Data Index: 1941127 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.7695. Min Act: -0.1700
Data Index: 1692622 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.7382. Min Act: -0.1700
Data Index: 5109666 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.7070. Min Act: -0.1700
Data Index: 1603996 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.7070. Min Act: -0.1700
Data Index: 2121960 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.7070. Min Act: -0.1700
Data Index: 4828148 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.7070. Min Act: -0.1700
Data Index: 5559718 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6757. Min Act: -0.1700
Data Index: 1910263 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6445. Min Act: -0.1700
Data Index: 4227926 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6445. Min Act: -0.1700
Data Index: 1603997 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6445. Min Act: -0.1700
Data Index: 6583132 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6445. Min Act: -0.1700
Data Index: 8274170 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6445. Min Act: -0.1700
Data Index: 8462479 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.5820. Min Act: -0.1700
Data Index: 227422 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6132. Min Act: -0.1700
Data Index: 5608974 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6132. Min Act: -0.1700
Data Index: 2589930 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6445. Min Act: -0.1700
Data Index: 916099 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6132. Min Act: -0.1700
Data Index: 8399031 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6445. Min Act: -0.1700
Data Index: 5014003 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8007. Min Range: -4.8007
Max Act: 4.6132. Min Act: -0.1700
Data Index: 5358895 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19