Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3818 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7842. Min Act: -0.1700
Data Index: 3493383 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7523. Min Act: -0.1700
Data Index: 6970620 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7203. Min Act: -0.1700
Data Index: 447890 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7043. Min Act: -0.1700
Data Index: 6765151 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7043. Min Act: -0.1700
Data Index: 1230020 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7043. Min Act: -0.1700
Data Index: 4737718 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7043. Min Act: -0.1700
Data Index: 7137258 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7043. Min Act: -0.1700
Data Index: 4170598 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7043. Min Act: -0.1700
Data Index: 2583657 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.7043. Min Act: -0.1700
Data Index: 2564507 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6883. Min Act: -0.1700
Data Index: 7144298 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6883. Min Act: -0.1700
Data Index: 7716293 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6883. Min Act: -0.1700
Data Index: 2339263 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6883. Min Act: -0.1700
Data Index: 6590350 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6883. Min Act: -0.1700
Data Index: 7301765 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6883. Min Act: -0.1700
Data Index: 7323408 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6723. Min Act: -0.1700
Data Index: 6575619 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6723. Min Act: -0.1700
Data Index: 1043422 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6723. Min Act: -0.1700
Data Index: 2713611 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7842. Min Range: -2.7842
Max Act: 2.6563. Min Act: -0.1700
Data Index: 5318350 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #19