Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4966 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6604. Min Range: -7.6604
Max Act: 7.6604. Min Act: -0.1700
Data Index: 954432 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6604. Min Range: -7.6604
Max Act: 7.2854. Min Act: -0.1700
Data Index: 543976 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6604. Min Range: -7.6604
Max Act: 7.2229. Min Act: -0.1700
Data Index: 6497994 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6604. Min Range: -7.6604
Max Act: 7.1916. Min Act: -0.1700
Data Index: 5656816 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6604. Min Range: -7.6604
Max Act: 7.1604. Min Act: -0.1700
Data Index: 6890746 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6604. Min Range: -7.6604
Max Act: 7.0666. Min Act: -0.1700
Data Index: 5665005 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6604. Min Range: -7.6604
Max Act: 7.0354. Min Act: -0.1700
Data Index: 588063 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.9104. Min Act: -0.1700
Data Index: 8089436 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.8791. Min Act: -0.1700
Data Index: 7726982 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7854. Min Act: -0.1700
Data Index: 4535683 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7854. Min Act: -0.1700
Data Index: 3247273 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7854. Min Act: -0.1700
Data Index: 8298519 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7541. Min Act: -0.1700
Data Index: 1252521 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7541. Min Act: -0.1700
Data Index: 1439621 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7229. Min Act: -0.1700
Data Index: 4423880 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7229. Min Act: -0.1700
Data Index: 7632728 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.7229. Min Act: -0.1700
Data Index: 335503 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.6916. Min Act: -0.1700
Data Index: 5178694 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.6604. Min Act: -0.1700
Data Index: 4841797 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6604. Min Range: -7.6604
Max Act: 6.6604. Min Act: -0.1700
Data Index: 1615078 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19