Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1044. Min Range: -5.1044
Max Act: 5.1044. Min Act: -0.1700
Data Index: 4300791 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1044. Min Range: -5.1044
Max Act: 5.0107. Min Act: -0.1700
Data Index: 2974290 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.9794. Min Act: -0.1700
Data Index: 8379660 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.9169. Min Act: -0.1700
Data Index: 7580888 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.9169. Min Act: -0.1700
Data Index: 2480702 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.8857. Min Act: -0.1700
Data Index: 2742499 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.8544. Min Act: -0.1700
Data Index: 3000072 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.8232. Min Act: -0.1700
Data Index: 7276452 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.8232. Min Act: -0.1700
Data Index: 22395 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.8232. Min Act: -0.1700
Data Index: 5514615 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7919. Min Act: -0.1700
Data Index: 1154872 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7919. Min Act: -0.1700
Data Index: 1013063 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7919. Min Act: -0.1700
Data Index: 1654636 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7919. Min Act: -0.1700
Data Index: 2390448 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.8232. Min Act: -0.1700
Data Index: 7535260 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7919. Min Act: -0.1700
Data Index: 4792670 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7919. Min Act: -0.1700
Data Index: 4722459 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7607. Min Act: -0.1700
Data Index: 5888828 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7607. Min Act: -0.1700
Data Index: 1091021 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1044. Min Range: -5.1044
Max Act: 4.7607. Min Act: -0.1700
Data Index: 1288826 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #19