Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4219 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0687. Min Range: -6.0687
Max Act: 6.0687. Min Act: -0.1700
Data Index: 1826885 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0687. Min Range: -6.0687
Max Act: 6.0062. Min Act: -0.1700
Data Index: 8504489 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.9125. Min Act: -0.1700
Data Index: 3336723 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.8812. Min Act: -0.1700
Data Index: 3946937 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.8500. Min Act: -0.1700
Data Index: 2993026 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.7875. Min Act: -0.1700
Data Index: 7884923 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.7562. Min Act: -0.1700
Data Index: 1569144 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.7562. Min Act: -0.1700
Data Index: 4493859 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6937. Min Act: -0.1700
Data Index: 3547555 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6937. Min Act: -0.1700
Data Index: 8072114 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6625. Min Act: -0.1700
Data Index: 6196174 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6312. Min Act: -0.1700
Data Index: 2190717 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6312. Min Act: -0.1700
Data Index: 4719418 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6312. Min Act: -0.1700
Data Index: 488671 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.5687. Min Act: -0.1700
Data Index: 5531046 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6000. Min Act: -0.1700
Data Index: 473031 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.6000. Min Act: -0.1700
Data Index: 7235534 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.5375. Min Act: -0.1700
Data Index: 2907128 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.5687. Min Act: -0.1700
Data Index: 6752214 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0687. Min Range: -6.0687
Max Act: 5.5375. Min Act: -0.1700
Data Index: 478587 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19