Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2672 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.5940. Min Act: -0.1700
Data Index: 998372 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.5628. Min Act: -0.1700
Data Index: 4815751 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.5315. Min Act: -0.1700
Data Index: 3409477 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4690. Min Act: -0.1700
Data Index: 2257108 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4378. Min Act: -0.1700
Data Index: 1535751 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4690. Min Act: -0.1700
Data Index: 4479536 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4065. Min Act: -0.1700
Data Index: 2732679 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4065. Min Act: -0.1700
Data Index: 6978587 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4065. Min Act: -0.1700
Data Index: 1809735 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4065. Min Act: -0.1700
Data Index: 6477593 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.4065. Min Act: -0.1700
Data Index: 865809 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3753. Min Act: -0.1700
Data Index: 2573940 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3753. Min Act: -0.1700
Data Index: 872338 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3753. Min Act: -0.1700
Data Index: 3409478 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3753. Min Act: -0.1700
Data Index: 8291575 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3440. Min Act: -0.1700
Data Index: 3231152 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3440. Min Act: -0.1700
Data Index: 1856898 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3440. Min Act: -0.1700
Data Index: 187241 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3128. Min Act: -0.1700
Data Index: 1150722 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5940. Min Range: -4.5940
Max Act: 4.3128. Min Act: -0.1700
Data Index: 5645620 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #19