Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4892 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.4506. Min Range: -12.4506
Max Act: 12.4506. Min Act: -0.1700
Data Index: 8398393 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.4506. Min Range: -12.4506
Max Act: 12.3881. Min Act: -0.1700
Data Index: 3509822 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.4506. Min Range: -12.4506
Max Act: 12.3881. Min Act: -0.1700
Data Index: 978340 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.8881. Min Act: -0.1700
Data Index: 5472654 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.8881. Min Act: -0.1700
Data Index: 4883108 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.8881. Min Act: -0.1700
Data Index: 4849893 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.8881. Min Act: -0.1700
Data Index: 6895886 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.8881. Min Act: -0.1700
Data Index: 8676755 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.8256. Min Act: -0.1700
Data Index: 7427768 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.7631. Min Act: -0.1700
Data Index: 6612910 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.7631. Min Act: -0.1700
Data Index: 4408065 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.7006. Min Act: -0.1700
Data Index: 4828242 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.7631. Min Act: -0.1700
Data Index: 4406470 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.7006. Min Act: -0.1700
Data Index: 97231 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.6381. Min Act: -0.1700
Data Index: 6807864 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.6381. Min Act: -0.1700
Data Index: 2175234 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.7006. Min Act: -0.1700
Data Index: 1168613 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.6381. Min Act: -0.1700
Data Index: 7506363 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.5756. Min Act: -0.1700
Data Index: 1817953 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.4506. Min Range: -12.4506
Max Act: 11.5756. Min Act: -0.1700
Data Index: 5186770 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #19