Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.5613. Min Act: -0.1700
Data Index: 3803982 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.5301. Min Act: -0.1700
Data Index: 6712583 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.3113. Min Act: -0.1700
Data Index: 7214885 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2801. Min Act: -0.1700
Data Index: 2829919 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2488. Min Act: -0.1700
Data Index: 2517350 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2488. Min Act: -0.1700
Data Index: 4315720 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2488. Min Act: -0.1700
Data Index: 3890 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.2488. Min Act: -0.1700
Data Index: 2342986 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1551. Min Act: -0.1700
Data Index: 1940346 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1551. Min Act: -0.1700
Data Index: 919796 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1551. Min Act: -0.1700
Data Index: 1737902 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1238. Min Act: -0.1700
Data Index: 4292293 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1238. Min Act: -0.1700
Data Index: 339775 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1238. Min Act: -0.1700
Data Index: 7690062 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1238. Min Act: -0.1700
Data Index: 6088014 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.1551. Min Act: -0.1700
Data Index: 1142685 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.0926. Min Act: -0.1700
Data Index: 4718726 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.0926. Min Act: -0.1700
Data Index: 2098658 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.0926. Min Act: -0.1700
Data Index: 2358193 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5613. Min Range: -5.5613
Max Act: 5.0613. Min Act: -0.1700
Data Index: 6922020 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #19