Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5034 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.7889. Min Act: -0.1700
Data Index: 918884 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.6327. Min Act: -0.1700
Data Index: 7796802 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5389. Min Act: -0.1700
Data Index: 1812146 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5389. Min Act: -0.1700
Data Index: 2220089 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5077. Min Act: -0.1700
Data Index: 1246735 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5389. Min Act: -0.1700
Data Index: 6847134 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5389. Min Act: -0.1700
Data Index: 6285754 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5077. Min Act: -0.1700
Data Index: 8172113 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 4594516 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5077. Min Act: -0.1700
Data Index: 4740982 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5077. Min Act: -0.1700
Data Index: 5653151 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5077. Min Act: -0.1700
Data Index: 6408655 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 571666 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 8073953 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 6252065 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 4750269 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 3068886 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.5077. Min Act: -0.1700
Data Index: 2641591 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 613634 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7889. Min Range: -4.7889
Max Act: 4.4764. Min Act: -0.1700
Data Index: 4360867 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #19