Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5715 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.6785. Min Act: -0.1700
Data Index: 2987248 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.1160. Min Act: -0.1700
Data Index: 8248745 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.1160. Min Act: -0.1700
Data Index: 1410808 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0848. Min Act: -0.1700
Data Index: 7400692 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0535. Min Act: -0.1700
Data Index: 2342937 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6785. Min Range: -7.6785
Max Act: 7.0223. Min Act: -0.1700
Data Index: 1822050 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9910. Min Act: -0.1700
Data Index: 5732837 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9598. Min Act: -0.1700
Data Index: 956979 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9598. Min Act: -0.1700
Data Index: 7282956 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9598. Min Act: -0.1700
Data Index: 4335584 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9598. Min Act: -0.1700
Data Index: 8094534 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.9285. Min Act: -0.1700
Data Index: 8741422 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.8660. Min Act: -0.1700
Data Index: 332445 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.8660. Min Act: -0.1700
Data Index: 8301580 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.8035. Min Act: -0.1700
Data Index: 4588045 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.8035. Min Act: -0.1700
Data Index: 8590386 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.8035. Min Act: -0.1700
Data Index: 825690 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.7723. Min Act: -0.1700
Data Index: 1605666 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.7723. Min Act: -0.1700
Data Index: 3704202 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6785. Min Range: -7.6785
Max Act: 6.7723. Min Act: -0.1700
Data Index: 4776751 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19