Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2830 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 17.8828. Min Range: -17.8828
Max Act: 17.8828. Min Act: -0.1700
Data Index: 3970454 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 17.8828. Min Range: -17.8828
Max Act: 17.6328. Min Act: -0.1700
Data Index: 1432026 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 17.8828. Min Range: -17.8828
Max Act: 17.3828. Min Act: -0.1700
Data Index: 4844989 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 17.8828. Min Range: -17.8828
Max Act: 17.2578. Min Act: -0.1700
Data Index: 709920 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 17.8828. Min Range: -17.8828
Max Act: 17.2578. Min Act: -0.1700
Data Index: 3752896 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 17.8828. Min Range: -17.8828
Max Act: 17.3828. Min Act: -0.1700
Data Index: 7505782 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 17.8828. Min Range: -17.8828
Max Act: 17.0078. Min Act: -0.1700
Data Index: 3534211 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.8828. Min Act: -0.1700
Data Index: 4152095 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.8828. Min Act: -0.1700
Data Index: 5032838 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.7578. Min Act: -0.1700
Data Index: 4141606 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.6328. Min Act: -0.1700
Data Index: 8004501 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.7578. Min Act: -0.1700
Data Index: 1629812 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.8828. Min Act: -0.1700
Data Index: 6348563 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.7578. Min Act: -0.1700
Data Index: 2063344 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.6328. Min Act: -0.1700
Data Index: 2707443 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.6328. Min Act: -0.1700
Data Index: 1802506 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.6328. Min Act: -0.1700
Data Index: 5740571 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.6328. Min Act: -0.1700
Data Index: 5946301 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.6328. Min Act: -0.1700
Data Index: 2811278 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 17.8828. Min Range: -17.8828
Max Act: 16.6328. Min Act: -0.1700
Data Index: 2915648 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #19