Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3853 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.2840. Min Act: -0.1700
Data Index: 6294546 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.2528. Min Act: -0.1700
Data Index: 4296578 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.1590. Min Act: -0.1700
Data Index: 1261875 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.0965. Min Act: -0.1700
Data Index: 5762871 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.0028. Min Act: -0.1700
Data Index: 6251143 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.0028. Min Act: -0.1700
Data Index: 6178799 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.0028. Min Act: -0.1700
Data Index: 4985342 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.9715. Min Act: -0.1700
Data Index: 863562 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2840. Min Range: -6.2840
Max Act: 6.0028. Min Act: -0.1700
Data Index: 2939893 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.9715. Min Act: -0.1700
Data Index: 458734 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.9403. Min Act: -0.1700
Data Index: 4731447 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.9090. Min Act: -0.1700
Data Index: 6562845 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8778. Min Act: -0.1700
Data Index: 20101 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8465. Min Act: -0.1700
Data Index: 5585140 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8153. Min Act: -0.1700
Data Index: 3628584 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8465. Min Act: -0.1700
Data Index: 3331585 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8465. Min Act: -0.1700
Data Index: 5399926 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8153. Min Act: -0.1700
Data Index: 5611144 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8465. Min Act: -0.1700
Data Index: 4922890 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2840. Min Range: -6.2840
Max Act: 5.8153. Min Act: -0.1700
Data Index: 1112216 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #19