Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3216 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1814. Min Act: -0.1700
Data Index: 7695248 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1502. Min Act: -0.1700
Data Index: 8697480 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1502. Min Act: -0.1700
Data Index: 5280393 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1502. Min Act: -0.1700
Data Index: 5047175 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1502. Min Act: -0.1700
Data Index: 7365250 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1502. Min Act: -0.1700
Data Index: 6990827 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1502. Min Act: -0.1700
Data Index: 3495328 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 2843049 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 5081014 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 222098 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0877. Min Act: -0.1700
Data Index: 3020649 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 5384126 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 5314639 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 6339990 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0877. Min Act: -0.1700
Data Index: 1467589 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 7785384 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.1189. Min Act: -0.1700
Data Index: 5082806 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0877. Min Act: -0.1700
Data Index: 6831051 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0877. Min Act: -0.1700
Data Index: 5700381 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1814. Min Range: -5.1814
Max Act: 5.0877. Min Act: -0.1700
Data Index: 444624 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19