Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1603 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.6738. Min Act: -0.1700
Data Index: 7245231 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.7050. Min Act: -0.1700
Data Index: 7669207 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.6738. Min Act: -0.1700
Data Index: 328157 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.6113. Min Act: -0.1700
Data Index: 878672 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.6113. Min Act: -0.1700
Data Index: 514075 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.5800. Min Act: -0.1700
Data Index: 5702365 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.5175. Min Act: -0.1700
Data Index: 7268254 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.4863. Min Act: -0.1700
Data Index: 7245230 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.4863. Min Act: -0.1700
Data Index: 3074414 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.4863. Min Act: -0.1700
Data Index: 7606681 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.4238. Min Act: -0.1700
Data Index: 2219849 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.4863. Min Act: -0.1700
Data Index: 8239111 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.4863. Min Act: -0.1700
Data Index: 7713118 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.4238. Min Act: -0.1700
Data Index: 4256645 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.3613. Min Act: -0.1700
Data Index: 7082934 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.3300. Min Act: -0.1700
Data Index: 5692137 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.2675. Min Act: -0.1700
Data Index: 674796 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.2988. Min Act: -0.1700
Data Index: 460704 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.2988. Min Act: -0.1700
Data Index: 771586 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7050. Min Range: -6.7050
Max Act: 6.2988. Min Act: -0.1700
Data Index: 262947 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #19