Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5711 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3785. Min Act: -0.1700
Data Index: 5460635 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3472. Min Act: -0.1700
Data Index: 4660946 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3160. Min Act: -0.1700
Data Index: 1164662 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.3160. Min Act: -0.1700
Data Index: 22813 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2847. Min Act: -0.1700
Data Index: 5982218 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.2535. Min Act: -0.1700
Data Index: 1892679 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 7595293 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 1742376 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1910. Min Act: -0.1700
Data Index: 3930209 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1597. Min Act: -0.1700
Data Index: 5499593 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1285. Min Act: -0.1700
Data Index: 44939 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1285. Min Act: -0.1700
Data Index: 6685686 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1285. Min Act: -0.1700
Data Index: 6917927 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0972. Min Act: -0.1700
Data Index: 8325146 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0972. Min Act: -0.1700
Data Index: 447097 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0972. Min Act: -0.1700
Data Index: 23081 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.1285. Min Act: -0.1700
Data Index: 8480590 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0972. Min Act: -0.1700
Data Index: 7178383 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0972. Min Act: -0.1700
Data Index: 6129158 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3785. Min Range: -4.3785
Max Act: 4.0972. Min Act: -0.1700
Data Index: 3369252 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19