Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1653 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2642. Min Range: -6.2642
Max Act: 6.2642. Min Act: -0.1700
Data Index: 6035443 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2642. Min Range: -6.2642
Max Act: 6.1704. Min Act: -0.1700
Data Index: 8309437 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.8267. Min Act: -0.1700
Data Index: 7910551 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5767. Min Act: -0.1700
Data Index: 7599519 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.6079. Min Act: -0.1700
Data Index: 3121503 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.6079. Min Act: -0.1700
Data Index: 5483366 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5767. Min Act: -0.1700
Data Index: 2095802 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5767. Min Act: -0.1700
Data Index: 4540964 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5454. Min Act: -0.1700
Data Index: 7794376 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5142. Min Act: -0.1700
Data Index: 5767812 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5454. Min Act: -0.1700
Data Index: 2505793 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5142. Min Act: -0.1700
Data Index: 8433952 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.5142. Min Act: -0.1700
Data Index: 8526735 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.4517. Min Act: -0.1700
Data Index: 417306 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.4204. Min Act: -0.1700
Data Index: 5493696 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.3892. Min Act: -0.1700
Data Index: 812684 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.3579. Min Act: -0.1700
Data Index: 2620891 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.3892. Min Act: -0.1700
Data Index: 6891399 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.3892. Min Act: -0.1700
Data Index: 2865772 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2642. Min Range: -6.2642
Max Act: 5.4204. Min Act: -0.1700
Data Index: 8401147 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #19