Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5390 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1059. Min Range: -8.1059
Max Act: 8.1059. Min Act: -0.1700
Data Index: 5248272 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1059. Min Range: -8.1059
Max Act: 8.0434. Min Act: -0.1700
Data Index: 944908 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.9809. Min Act: -0.1700
Data Index: 4468332 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1059. Min Range: -8.1059
Max Act: 8.0434. Min Act: -0.1700
Data Index: 7610141 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1059. Min Range: -8.1059
Max Act: 8.0434. Min Act: -0.1700
Data Index: 2429241 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1059. Min Range: -8.1059
Max Act: 8.0434. Min Act: -0.1700
Data Index: 594600 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.9809. Min Act: -0.1700
Data Index: 2652700 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.9809. Min Act: -0.1700
Data Index: 7953054 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.9809. Min Act: -0.1700
Data Index: 8813701 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.9809. Min Act: -0.1700
Data Index: 3223424 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.9184. Min Act: -0.1700
Data Index: 2619389 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.8559. Min Act: -0.1700
Data Index: 1065998 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.7934. Min Act: -0.1700
Data Index: 3139930 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.8559. Min Act: -0.1700
Data Index: 6843712 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.7934. Min Act: -0.1700
Data Index: 6794521 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.7934. Min Act: -0.1700
Data Index: 4120586 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.7934. Min Act: -0.1700
Data Index: 8669666 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.7309. Min Act: -0.1700
Data Index: 5546907 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.7309. Min Act: -0.1700
Data Index: 4209642 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1059. Min Range: -8.1059
Max Act: 7.7309. Min Act: -0.1700
Data Index: 7431642 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #19