Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3170 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.5504. Min Act: -0.1700
Data Index: 8442061 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.5192. Min Act: -0.1700
Data Index: 2352206 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3629. Min Act: -0.1700
Data Index: 669894 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3942. Min Act: -0.1700
Data Index: 3437021 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3629. Min Act: -0.1700
Data Index: 4642251 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3317. Min Act: -0.1700
Data Index: 5463716 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3317. Min Act: -0.1700
Data Index: 2148850 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3317. Min Act: -0.1700
Data Index: 3898688 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3317. Min Act: -0.1700
Data Index: 8222626 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3004. Min Act: -0.1700
Data Index: 4150935 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3004. Min Act: -0.1700
Data Index: 4202260 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3004. Min Act: -0.1700
Data Index: 4187698 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2692. Min Act: -0.1700
Data Index: 4836426 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.3004. Min Act: -0.1700
Data Index: 718856 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7386751 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2692. Min Act: -0.1700
Data Index: 2344908 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2692. Min Act: -0.1700
Data Index: 922218 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2379. Min Act: -0.1700
Data Index: 6606315 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2379. Min Act: -0.1700
Data Index: 7264502 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5504. Min Range: -5.5504
Max Act: 5.2379. Min Act: -0.1700
Data Index: 651563 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19