Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1868 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.9724. Min Act: -0.1700
Data Index: 2122762 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.7224. Min Act: -0.1700
Data Index: 1623068 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.6911. Min Act: -0.1700
Data Index: 3466044 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.5974. Min Act: -0.1700
Data Index: 1202292 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.5661. Min Act: -0.1700
Data Index: 8612785 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.5036. Min Act: -0.1700
Data Index: 8188717 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.5036. Min Act: -0.1700
Data Index: 5249617 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 5094052 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 7184501 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 8213741 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 1444121 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4724. Min Act: -0.1700
Data Index: 3741529 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4411. Min Act: -0.1700
Data Index: 7711949 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4411. Min Act: -0.1700
Data Index: 2204540 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.3786. Min Act: -0.1700
Data Index: 1248465 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4099. Min Act: -0.1700
Data Index: 4295872 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4099. Min Act: -0.1700
Data Index: 8404996 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.4099. Min Act: -0.1700
Data Index: 6293838 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.3786. Min Act: -0.1700
Data Index: 5141947 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9724. Min Range: -6.9724
Max Act: 6.3786. Min Act: -0.1700
Data Index: 6839237 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #19