Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4139 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.3745. Min Act: -0.1700
Data Index: 1758641 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.3432. Min Act: -0.1700
Data Index: 4618590 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.3432. Min Act: -0.1700
Data Index: 5384564 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.3120. Min Act: -0.1700
Data Index: 3034236 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.2495. Min Act: -0.1700
Data Index: 1438418 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.2495. Min Act: -0.1700
Data Index: 7022196 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.1870. Min Act: -0.1700
Data Index: 5158608 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.1245. Min Act: -0.1700
Data Index: 894489 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.1245. Min Act: -0.1700
Data Index: 7467085 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.0620. Min Act: -0.1700
Data Index: 7779633 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.0620. Min Act: -0.1700
Data Index: 7554428 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.0307. Min Act: -0.1700
Data Index: 3066391 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.0307. Min Act: -0.1700
Data Index: 1514675 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3745. Min Range: -7.3745
Max Act: 6.9995. Min Act: -0.1700
Data Index: 2779713 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3745. Min Range: -7.3745
Max Act: 7.0307. Min Act: -0.1700
Data Index: 4614344 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3745. Min Range: -7.3745
Max Act: 6.9995. Min Act: -0.1700
Data Index: 2942905 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3745. Min Range: -7.3745
Max Act: 6.9682. Min Act: -0.1700
Data Index: 439635 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3745. Min Range: -7.3745
Max Act: 6.9370. Min Act: -0.1700
Data Index: 615805 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3745. Min Range: -7.3745
Max Act: 6.9057. Min Act: -0.1700
Data Index: 512971 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3745. Min Range: -7.3745
Max Act: 6.8745. Min Act: -0.1700
Data Index: 7029905 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #19