Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3449 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0639. Min Range: -6.0639
Max Act: 6.0639. Min Act: -0.1700
Data Index: 8807518 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0639. Min Range: -6.0639
Max Act: 6.0326. Min Act: -0.1700
Data Index: 4541481 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0639. Min Range: -6.0639
Max Act: 6.0014. Min Act: -0.1700
Data Index: 7895863 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9701. Min Act: -0.1700
Data Index: 3493003 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9389. Min Act: -0.1700
Data Index: 7136867 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9389. Min Act: -0.1700
Data Index: 1473096 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9076. Min Act: -0.1700
Data Index: 6544463 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9076. Min Act: -0.1700
Data Index: 4179235 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9389. Min Act: -0.1700
Data Index: 8517985 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9076. Min Act: -0.1700
Data Index: 3708515 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9076. Min Act: -0.1700
Data Index: 6836052 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.9076. Min Act: -0.1700
Data Index: 6236428 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8764. Min Act: -0.1700
Data Index: 3025660 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8764. Min Act: -0.1700
Data Index: 4388436 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8451. Min Act: -0.1700
Data Index: 8163908 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8451. Min Act: -0.1700
Data Index: 941991 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8451. Min Act: -0.1700
Data Index: 1974804 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8451. Min Act: -0.1700
Data Index: 4470948 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8139. Min Act: -0.1700
Data Index: 7601480 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0639. Min Range: -6.0639
Max Act: 5.8764. Min Act: -0.1700
Data Index: 6808550 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #19