Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3554 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.9194. Min Act: -0.1700
Data Index: 216716 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.8882. Min Act: -0.1700
Data Index: 524825 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.8569. Min Act: -0.1700
Data Index: 6406558 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7632. Min Act: -0.1700
Data Index: 923319 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7632. Min Act: -0.1700
Data Index: 4862531 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7632. Min Act: -0.1700
Data Index: 5231379 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7632. Min Act: -0.1700
Data Index: 637481 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7632. Min Act: -0.1700
Data Index: 7377886 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7632. Min Act: -0.1700
Data Index: 5040270 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7319. Min Act: -0.1700
Data Index: 24028 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7007. Min Act: -0.1700
Data Index: 6337022 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.6694. Min Act: -0.1700
Data Index: 1006028 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7007. Min Act: -0.1700
Data Index: 4940560 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7007. Min Act: -0.1700
Data Index: 7288272 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.7007. Min Act: -0.1700
Data Index: 7171027 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.6694. Min Act: -0.1700
Data Index: 4652748 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.6694. Min Act: -0.1700
Data Index: 7690921 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.6694. Min Act: -0.1700
Data Index: 823541 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.6694. Min Act: -0.1700
Data Index: 3913725 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9194. Min Range: -4.9194
Max Act: 4.6694. Min Act: -0.1700
Data Index: 3163143 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #19