Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3820 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3645. Min Range: -6.3645
Max Act: 6.3645. Min Act: -0.1700
Data Index: 553537 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3645. Min Range: -6.3645
Max Act: 6.2707. Min Act: -0.1700
Data Index: 7564538 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3645. Min Range: -6.3645
Max Act: 6.1770. Min Act: -0.1700
Data Index: 6123756 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3645. Min Range: -6.3645
Max Act: 6.0832. Min Act: -0.1700
Data Index: 7539025 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3645. Min Range: -6.3645
Max Act: 6.0832. Min Act: -0.1700
Data Index: 8237130 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3645. Min Range: -6.3645
Max Act: 6.0207. Min Act: -0.1700
Data Index: 3660384 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3645. Min Range: -6.3645
Max Act: 6.0207. Min Act: -0.1700
Data Index: 6436709 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.9582. Min Act: -0.1700
Data Index: 3901766 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.9270. Min Act: -0.1700
Data Index: 6234560 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8645. Min Act: -0.1700
Data Index: 5808610 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8332. Min Act: -0.1700
Data Index: 6746564 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8645. Min Act: -0.1700
Data Index: 7718525 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8332. Min Act: -0.1700
Data Index: 4557599 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8332. Min Act: -0.1700
Data Index: 3467015 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8020. Min Act: -0.1700
Data Index: 1678172 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8020. Min Act: -0.1700
Data Index: 5972870 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.7707. Min Act: -0.1700
Data Index: 1497776 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.8020. Min Act: -0.1700
Data Index: 5124895 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.7707. Min Act: -0.1700
Data Index: 3692950 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3645. Min Range: -6.3645
Max Act: 5.7082. Min Act: -0.1700
Data Index: 7250087 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #19