Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5864 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2289. Min Range: -7.2289
Max Act: 7.2289. Min Act: -0.1700
Data Index: 1810583 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.9789. Min Act: -0.1700
Data Index: 6937444 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.9477. Min Act: -0.1700
Data Index: 7607795 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.9477. Min Act: -0.1700
Data Index: 3766039 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.9164. Min Act: -0.1700
Data Index: 18865 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.9164. Min Act: -0.1700
Data Index: 1933742 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.8539. Min Act: -0.1700
Data Index: 3552571 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.8539. Min Act: -0.1700
Data Index: 2082145 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.8539. Min Act: -0.1700
Data Index: 7177245 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.8227. Min Act: -0.1700
Data Index: 380225 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.8227. Min Act: -0.1700
Data Index: 4083666 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.8227. Min Act: -0.1700
Data Index: 7919583 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.8227. Min Act: -0.1700
Data Index: 1665631 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.7602. Min Act: -0.1700
Data Index: 6086007 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.7602. Min Act: -0.1700
Data Index: 5912847 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 6034740 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.7602. Min Act: -0.1700
Data Index: 5719288 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.7289. Min Act: -0.1700
Data Index: 501680 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.6977. Min Act: -0.1700
Data Index: 5027866 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2289. Min Range: -7.2289
Max Act: 6.6977. Min Act: -0.1700
Data Index: 5789597 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #19