Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4243 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.9103. Min Act: -0.1700
Data Index: 1447694 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.8478. Min Act: -0.1700
Data Index: 5579368 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.7853. Min Act: -0.1700
Data Index: 1522574 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.6603. Min Act: -0.1700
Data Index: 122588 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.6603. Min Act: -0.1700
Data Index: 8823841 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.6603. Min Act: -0.1700
Data Index: 4017820 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 5251898 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5978. Min Act: -0.1700
Data Index: 2078776 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5978. Min Act: -0.1700
Data Index: 3799885 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 3867205 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 8793647 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 8293374 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 2518891 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 6776579 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 5932181 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 3664758 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 5625648 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.4728. Min Act: -0.1700
Data Index: 7423470 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.5353. Min Act: -0.1700
Data Index: 399246 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9103. Min Range: -8.9103
Max Act: 8.4728. Min Act: -0.1700
Data Index: 3908142 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #19