Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 231 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.7125. Min Act: -0.1700
Data Index: 2169673 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.7125. Min Act: -0.1700
Data Index: 2219415 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.7125. Min Act: -0.1700
Data Index: 3488678 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6812. Min Act: -0.1700
Data Index: 8598573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6812. Min Act: -0.1700
Data Index: 7322440 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6812. Min Act: -0.1700
Data Index: 1119677 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 1920438 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 4456905 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 1905859 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6186. Min Act: -0.1700
Data Index: 470391 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 4189154 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6186. Min Act: -0.1700
Data Index: 3661134 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 3412744 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6186. Min Act: -0.1700
Data Index: 3098632 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2752364 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2600978 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2336467 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2320741 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2149558 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7125. Min Range: -3.7125
Max Act: 3.6499. Min Act: -0.1700
Data Index: 2095250 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19