Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4196 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.1535. Min Act: -0.1700
Data Index: 681373 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.1535. Min Act: -0.1700
Data Index: 473557 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.1222. Min Act: -0.1700
Data Index: 4292851 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.1222. Min Act: -0.1700
Data Index: 318215 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.1222. Min Act: -0.1700
Data Index: 4292849 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0910. Min Act: -0.1700
Data Index: 4725908 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0910. Min Act: -0.1700
Data Index: 4725909 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0910. Min Act: -0.1700
Data Index: 3967111 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0910. Min Act: -0.1700
Data Index: 4725907 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0910. Min Act: -0.1700
Data Index: 6201223 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0597. Min Act: -0.1700
Data Index: 4725911 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0597. Min Act: -0.1700
Data Index: 7793808 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0597. Min Act: -0.1700
Data Index: 6201226 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0597. Min Act: -0.1700
Data Index: 6201229 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0597. Min Act: -0.1700
Data Index: 2938523 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0285. Min Act: -0.1700
Data Index: 6201221 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0285. Min Act: -0.1700
Data Index: 6454243 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0285. Min Act: -0.1700
Data Index: 6054765 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0285. Min Act: -0.1700
Data Index: 5657173 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1535. Min Range: -4.1535
Max Act: 4.0285. Min Act: -0.1700
Data Index: 4292850 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #19