Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2588 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0251. Min Range: -4.0251
Max Act: 4.0251. Min Act: -0.1700
Data Index: 833088 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0251. Min Range: -4.0251
Max Act: 4.0251. Min Act: -0.1700
Data Index: 7129330 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9938. Min Act: -0.1700
Data Index: 5966925 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9938. Min Act: -0.1700
Data Index: 3741435 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9626. Min Act: -0.1700
Data Index: 7992128 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9000. Min Act: -0.1700
Data Index: 5358888 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9000. Min Act: -0.1700
Data Index: 1880411 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9000. Min Act: -0.1700
Data Index: 8373386 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.9000. Min Act: -0.1700
Data Index: 3762893 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8844. Min Act: -0.1700
Data Index: 4342930 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8688. Min Act: -0.1700
Data Index: 233026 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8531. Min Act: -0.1700
Data Index: 8601706 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 1238487 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8688. Min Act: -0.1700
Data Index: 3849934 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8531. Min Act: -0.1700
Data Index: 8456884 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8531. Min Act: -0.1700
Data Index: 1927386 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8531. Min Act: -0.1700
Data Index: 7294025 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 2439774 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8375. Min Act: -0.1700
Data Index: 5956556 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0251. Min Range: -4.0251
Max Act: 3.8219. Min Act: -0.1700
Data Index: 3574509 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19