Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3107 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3498. Min Range: -6.3498
Max Act: 6.3498. Min Act: -0.1700
Data Index: 325289 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3498. Min Range: -6.3498
Max Act: 6.0060. Min Act: -0.1700
Data Index: 6938162 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3498. Min Range: -6.3498
Max Act: 6.0060. Min Act: -0.1700
Data Index: 8785292 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3498. Min Range: -6.3498
Max Act: 6.0060. Min Act: -0.1700
Data Index: 5721108 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.9435. Min Act: -0.1700
Data Index: 5014911 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.9435. Min Act: -0.1700
Data Index: 6831444 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.9123. Min Act: -0.1700
Data Index: 583252 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8810. Min Act: -0.1700
Data Index: 262966 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8498. Min Act: -0.1700
Data Index: 3716475 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8498. Min Act: -0.1700
Data Index: 8286335 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8498. Min Act: -0.1700
Data Index: 654812 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8185. Min Act: -0.1700
Data Index: 1909684 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8185. Min Act: -0.1700
Data Index: 4411548 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8185. Min Act: -0.1700
Data Index: 3641322 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8185. Min Act: -0.1700
Data Index: 4832880 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8185. Min Act: -0.1700
Data Index: 7779126 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.8185. Min Act: -0.1700
Data Index: 2535349 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.7873. Min Act: -0.1700
Data Index: 5641384 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.7560. Min Act: -0.1700
Data Index: 2972424 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3498. Min Range: -6.3498
Max Act: 5.7560. Min Act: -0.1700
Data Index: 6254187 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19