Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5099 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1718. Min Range: -7.1718
Max Act: 7.1718. Min Act: -0.1700
Data Index: 6991592 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.9531. Min Act: -0.1700
Data Index: 5028847 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.9218. Min Act: -0.1700
Data Index: 8197381 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.9218. Min Act: -0.1700
Data Index: 4169283 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.8593. Min Act: -0.1700
Data Index: 272578 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.7656. Min Act: -0.1700
Data Index: 221570 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.7656. Min Act: -0.1700
Data Index: 4175578 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.7343. Min Act: -0.1700
Data Index: 8121798 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.7031. Min Act: -0.1700
Data Index: 5174932 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.6406. Min Act: -0.1700
Data Index: 7629100 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.5781. Min Act: -0.1700
Data Index: 2092153 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.5781. Min Act: -0.1700
Data Index: 5421346 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.6093. Min Act: -0.1700
Data Index: 5438739 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.6093. Min Act: -0.1700
Data Index: 31245 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.6093. Min Act: -0.1700
Data Index: 3043140 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.5468. Min Act: -0.1700
Data Index: 4869376 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.5781. Min Act: -0.1700
Data Index: 4493053 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.5156. Min Act: -0.1700
Data Index: 4698632 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.5156. Min Act: -0.1700
Data Index: 3943351 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1718. Min Range: -7.1718
Max Act: 6.5156. Min Act: -0.1700
Data Index: 5105742 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #19