Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3384 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.4988. Min Act: -0.1700
Data Index: 911803 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.4675. Min Act: -0.1700
Data Index: 263127 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.4363. Min Act: -0.1700
Data Index: 4918694 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.3738. Min Act: -0.1700
Data Index: 7304595 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.3425. Min Act: -0.1700
Data Index: 1801422 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.3113. Min Act: -0.1700
Data Index: 5904590 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.3113. Min Act: -0.1700
Data Index: 2170294 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2800. Min Act: -0.1700
Data Index: 4399949 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.3113. Min Act: -0.1700
Data Index: 4424831 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2800. Min Act: -0.1700
Data Index: 401539 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2488. Min Act: -0.1700
Data Index: 3997121 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2175. Min Act: -0.1700
Data Index: 2465834 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2175. Min Act: -0.1700
Data Index: 5904588 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2488. Min Act: -0.1700
Data Index: 2345557 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2488. Min Act: -0.1700
Data Index: 3157695 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2488. Min Act: -0.1700
Data Index: 5535865 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2488. Min Act: -0.1700
Data Index: 1039132 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2488. Min Act: -0.1700
Data Index: 3527399 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2800. Min Act: -0.1700
Data Index: 7558431 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4988. Min Range: -4.4988
Max Act: 4.2175. Min Act: -0.1700
Data Index: 3246221 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19