Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5416 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.5595. Min Act: -0.1700
Data Index: 4502565 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.5908. Min Act: -0.1700
Data Index: 6122295 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.5595. Min Act: -0.1700
Data Index: 259964 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4969. Min Act: -0.1700
Data Index: 3197904 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.5126. Min Act: -0.1700
Data Index: 7559734 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4812. Min Act: -0.1700
Data Index: 2435068 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4969. Min Act: -0.1700
Data Index: 342653 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4342. Min Act: -0.1700
Data Index: 3197915 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4186. Min Act: -0.1700
Data Index: 3197913 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4029. Min Act: -0.1700
Data Index: 3353759 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.4029. Min Act: -0.1700
Data Index: 44654 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3715. Min Act: -0.1700
Data Index: 3197912 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3715. Min Act: -0.1700
Data Index: 3197901 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 7389921 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 1616838 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3401. Min Act: -0.1700
Data Index: 3274751 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3245. Min Act: -0.1700
Data Index: 3343540 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 8424402 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3401. Min Act: -0.1700
Data Index: 3197907 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5908. Min Range: -3.5908
Max Act: 3.3558. Min Act: -0.1700
Data Index: 3353758 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19