Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3232 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.7870. Min Act: -0.1700
Data Index: 2823676 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.7870. Min Act: -0.1700
Data Index: 7644734 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.7558. Min Act: -0.1700
Data Index: 1060031 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.7245. Min Act: -0.1700
Data Index: 2691200 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6933. Min Act: -0.1700
Data Index: 7417670 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6933. Min Act: -0.1700
Data Index: 7151025 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6620. Min Act: -0.1700
Data Index: 3919801 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6620. Min Act: -0.1700
Data Index: 1193687 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6620. Min Act: -0.1700
Data Index: 5016503 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6620. Min Act: -0.1700
Data Index: 45494 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6620. Min Act: -0.1700
Data Index: 6961334 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6620. Min Act: -0.1700
Data Index: 6260633 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6308. Min Act: -0.1700
Data Index: 4159433 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6308. Min Act: -0.1700
Data Index: 7151027 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.5995. Min Act: -0.1700
Data Index: 4038313 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.6308. Min Act: -0.1700
Data Index: 595383 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.5995. Min Act: -0.1700
Data Index: 8771419 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.5995. Min Act: -0.1700
Data Index: 843736 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.5995. Min Act: -0.1694
Data Index: 4177646 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7870. Min Range: -4.7870
Max Act: 4.5683. Min Act: -0.1700
Data Index: 1915837 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #19