Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 655 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.8963. Min Act: -0.1700
Data Index: 6609473 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.8026. Min Act: -0.1700
Data Index: 7404573 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.8026. Min Act: -0.1700
Data Index: 5923027 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.7713. Min Act: -0.1700
Data Index: 6273079 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.7401. Min Act: -0.1700
Data Index: 7188981 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.7401. Min Act: -0.1700
Data Index: 7404571 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.7088. Min Act: -0.1700
Data Index: 5660714 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.7088. Min Act: -0.1700
Data Index: 1938734 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.7088. Min Act: -0.1700
Data Index: 3009263 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.7088. Min Act: -0.1700
Data Index: 668184 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6776. Min Act: -0.1700
Data Index: 4984763 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6463. Min Act: -0.1700
Data Index: 4990829 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6776. Min Act: -0.1700
Data Index: 7417538 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6151. Min Act: -0.1700
Data Index: 4030507 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6151. Min Act: -0.1700
Data Index: 5729622 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6151. Min Act: -0.1700
Data Index: 6902278 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.5838. Min Act: -0.1700
Data Index: 6479361 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6151. Min Act: -0.1700
Data Index: 513679 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.6151. Min Act: -0.1700
Data Index: 2796529 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8963. Min Range: -5.8963
Max Act: 5.5838. Min Act: -0.1700
Data Index: 1116254 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19