Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5010 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7782. Min Range: -7.7782
Max Act: 7.7782. Min Act: -0.1700
Data Index: 8796162 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.7157. Min Act: -0.1700
Data Index: 332856 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.4345. Min Act: -0.1700
Data Index: 5535821 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.4657. Min Act: -0.1700
Data Index: 2010044 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.4032. Min Act: -0.1700
Data Index: 8188377 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.3407. Min Act: -0.1700
Data Index: 3937512 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.3407. Min Act: -0.1700
Data Index: 8259029 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.3407. Min Act: -0.1700
Data Index: 4782733 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.3407. Min Act: -0.1700
Data Index: 3552142 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.3095. Min Act: -0.1700
Data Index: 6194720 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.2782. Min Act: -0.1700
Data Index: 3463994 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.2782. Min Act: -0.1700
Data Index: 2092698 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.3095. Min Act: -0.1700
Data Index: 700697 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.2470. Min Act: -0.1700
Data Index: 1059664 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.2157. Min Act: -0.1700
Data Index: 1130809 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.1532. Min Act: -0.1700
Data Index: 759779 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.1532. Min Act: -0.1700
Data Index: 4616034 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.1220. Min Act: -0.1700
Data Index: 2312458 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.1220. Min Act: -0.1700
Data Index: 6861330 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7782. Min Range: -7.7782
Max Act: 6.1220. Min Act: -0.1700
Data Index: 3240316 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #19