Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 47 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2093. Min Range: -8.2093
Max Act: 8.2093. Min Act: -0.1700
Data Index: 8592211 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2093. Min Range: -8.2093
Max Act: 8.0218. Min Act: -0.1700
Data Index: 1454665 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.9593. Min Act: -0.1700
Data Index: 7146887 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.9593. Min Act: -0.1700
Data Index: 7255253 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.9593. Min Act: -0.1700
Data Index: 7255251 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.8968. Min Act: -0.1700
Data Index: 4159991 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.8343. Min Act: -0.1700
Data Index: 5194001 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.8343. Min Act: -0.1700
Data Index: 6205632 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.8343. Min Act: -0.1700
Data Index: 5194002 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.8343. Min Act: -0.1700
Data Index: 3002862 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.8031. Min Act: -0.1700
Data Index: 7502157 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7718. Min Act: -0.1700
Data Index: 5194026 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7406. Min Act: -0.1700
Data Index: 5194007 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7406. Min Act: -0.1700
Data Index: 5194012 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7718. Min Act: -0.1700
Data Index: 3692887 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7093. Min Act: -0.1700
Data Index: 5194000 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7093. Min Act: -0.1700
Data Index: 5194008 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7093. Min Act: -0.1700
Data Index: 5194006 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7093. Min Act: -0.1700
Data Index: 5194028 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2093. Min Range: -8.2093
Max Act: 7.7406. Min Act: -0.1700
Data Index: 5194029 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #19