Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4652 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.9751. Min Act: -0.1700
Data Index: 961332 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.8501. Min Act: -0.1700
Data Index: 2762931 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.6001. Min Act: -0.1700
Data Index: 8369991 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.5689. Min Act: -0.1700
Data Index: 4564764 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.2564. Min Act: -0.1700
Data Index: 2226636 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.2251. Min Act: -0.1700
Data Index: 6937735 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.1939. Min Act: -0.1700
Data Index: 6974269 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.1626. Min Act: -0.1700
Data Index: 8266512 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.1314. Min Act: -0.1700
Data Index: 7007943 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.1001. Min Act: -0.1700
Data Index: 6770405 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4898014 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.0376. Min Act: -0.1700
Data Index: 3869767 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.0689. Min Act: -0.1700
Data Index: 4716480 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9751. Min Range: -7.9751
Max Act: 7.0064. Min Act: -0.1700
Data Index: 4866447 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9751. Min Range: -7.9751
Max Act: 6.9126. Min Act: -0.1700
Data Index: 1342428 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9751. Min Range: -7.9751
Max Act: 6.9439. Min Act: -0.1700
Data Index: 6866312 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9751. Min Range: -7.9751
Max Act: 6.9439. Min Act: -0.1700
Data Index: 5161686 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9751. Min Range: -7.9751
Max Act: 6.9126. Min Act: -0.1700
Data Index: 7396035 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9751. Min Range: -7.9751
Max Act: 6.9126. Min Act: -0.1700
Data Index: 5356634 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9751. Min Range: -7.9751
Max Act: 6.8814. Min Act: -0.1700
Data Index: 7993371 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #19