Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.6906. Min Act: -0.1700
Data Index: 7502064 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.3469. Min Act: -0.1700
Data Index: 823660 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.3469. Min Act: -0.1700
Data Index: 2452422 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.3469. Min Act: -0.1700
Data Index: 1595403 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.3469. Min Act: -0.1700
Data Index: 5820127 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.3469. Min Act: -0.1700
Data Index: 708191 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2844. Min Act: -0.1700
Data Index: 1992689 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2844. Min Act: -0.1700
Data Index: 7760103 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2844. Min Act: -0.1700
Data Index: 7546396 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2219. Min Act: -0.1700
Data Index: 7011459 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2531. Min Act: -0.1700
Data Index: 8039976 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2531. Min Act: -0.1700
Data Index: 4493501 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2531. Min Act: -0.1700
Data Index: 501368 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2219. Min Act: -0.1700
Data Index: 6541799 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2531. Min Act: -0.1700
Data Index: 8746429 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.2219. Min Act: -0.1700
Data Index: 1245761 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.1906. Min Act: -0.1700
Data Index: 6100562 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.1594. Min Act: -0.1700
Data Index: 6875792 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.1906. Min Act: -0.1700
Data Index: 4693610 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6906. Min Range: -6.6906
Max Act: 6.1594. Min Act: -0.1700
Data Index: 7158765 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19