Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5935 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0278. Min Range: -5.0278
Max Act: 5.0278. Min Act: -0.1700
Data Index: 3732166 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.7153. Min Act: -0.1700
Data Index: 661205 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.5591. Min Act: -0.1700
Data Index: 5191219 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.5278. Min Act: -0.1700
Data Index: 2217412 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.4028. Min Act: -0.1700
Data Index: 6335973 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.4028. Min Act: -0.1700
Data Index: 4655868 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3716. Min Act: -0.1700
Data Index: 6662640 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3716. Min Act: -0.1700
Data Index: 3424180 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3716. Min Act: -0.1700
Data Index: 1795997 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3403. Min Act: -0.1700
Data Index: 8526613 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3091. Min Act: -0.1700
Data Index: 42683 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3403. Min Act: -0.1700
Data Index: 6151194 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3403. Min Act: -0.1700
Data Index: 2721997 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3403. Min Act: -0.1700
Data Index: 3151636 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3403. Min Act: -0.1700
Data Index: 3876708 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3403. Min Act: -0.1700
Data Index: 5366108 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3403. Min Act: -0.1700
Data Index: 7347416 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3091. Min Act: -0.1700
Data Index: 6988738 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3091. Min Act: -0.1700
Data Index: 6488009 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0278. Min Range: -5.0278
Max Act: 4.3091. Min Act: -0.1700
Data Index: 3816094 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #19