Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1742 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.3452. Min Act: -0.1700
Data Index: 2763522 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.2514. Min Act: -0.1700
Data Index: 2712136 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.2514. Min Act: -0.1700
Data Index: 8815090 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.2202. Min Act: -0.1700
Data Index: 2081573 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.1889. Min Act: -0.1700
Data Index: 2998818 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.1577. Min Act: -0.1700
Data Index: 26197 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.0952. Min Act: -0.1700
Data Index: 8232975 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.0639. Min Act: -0.1700
Data Index: 271546 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.0014. Min Act: -0.1700
Data Index: 4037730 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.0327. Min Act: -0.1700
Data Index: 5222538 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.0014. Min Act: -0.1700
Data Index: 3000 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9702. Min Act: -0.1700
Data Index: 688113 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3452. Min Range: -6.3452
Max Act: 6.0014. Min Act: -0.1700
Data Index: 7772046 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9702. Min Act: -0.1700
Data Index: 1867636 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9702. Min Act: -0.1700
Data Index: 3097601 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9702. Min Act: -0.1700
Data Index: 7307160 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9702. Min Act: -0.1700
Data Index: 2444856 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9702. Min Act: -0.1700
Data Index: 360026 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9389. Min Act: -0.1700
Data Index: 2150834 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3452. Min Range: -6.3452
Max Act: 5.9389. Min Act: -0.1700
Data Index: 5159409 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19