Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2907 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.5762. Min Act: -0.1700
Data Index: 2030625 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.5449. Min Act: -0.1700
Data Index: 2810912 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.5137. Min Act: -0.1700
Data Index: 995755 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.4824. Min Act: -0.1700
Data Index: 12036 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.4824. Min Act: -0.1700
Data Index: 52512 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.4512. Min Act: -0.1700
Data Index: 1896540 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.4199. Min Act: -0.1700
Data Index: 2884935 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.4199. Min Act: -0.1700
Data Index: 5748377 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.3574. Min Act: -0.1700
Data Index: 6601548 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.3574. Min Act: -0.1700
Data Index: 4390749 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.3262. Min Act: -0.1700
Data Index: 7684190 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2637. Min Act: -0.1700
Data Index: 2580651 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2949. Min Act: -0.1700
Data Index: 2077037 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2949. Min Act: -0.1700
Data Index: 5298735 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2637. Min Act: -0.1700
Data Index: 3076059 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2949. Min Act: -0.1700
Data Index: 6377932 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2324. Min Act: -0.1700
Data Index: 7360372 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2324. Min Act: -0.1700
Data Index: 1609848 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2324. Min Act: -0.1700
Data Index: 6964596 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5762. Min Range: -5.5762
Max Act: 5.2012. Min Act: -0.1700
Data Index: 1013272 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19