Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1641 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.9064. Min Act: -0.1700
Data Index: 4880131 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.6251. Min Act: -0.1700
Data Index: 250946 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.5626. Min Act: -0.1700
Data Index: 7018631 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.5626. Min Act: -0.1700
Data Index: 1074748 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.5001. Min Act: -0.1700
Data Index: 264064 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.4689. Min Act: -0.1700
Data Index: 1624086 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.3751. Min Act: -0.1700
Data Index: 3513025 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.4064. Min Act: -0.1700
Data Index: 5439392 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.4064. Min Act: -0.1700
Data Index: 8183287 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.3439. Min Act: -0.1700
Data Index: 6732863 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.3439. Min Act: -0.1700
Data Index: 2800635 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.3126. Min Act: -0.1700
Data Index: 7559079 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.3126. Min Act: -0.1700
Data Index: 1049454 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.3439. Min Act: -0.1700
Data Index: 4842806 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.3126. Min Act: -0.1700
Data Index: 1500083 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.2814. Min Act: -0.1700
Data Index: 2044598 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.2814. Min Act: -0.1700
Data Index: 200752 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.2501. Min Act: -0.1700
Data Index: 3579673 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.2814. Min Act: -0.1700
Data Index: 8131773 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9064. Min Range: -5.9064
Max Act: 5.2814. Min Act: -0.1700
Data Index: 3834182 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #19