Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4076 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.3705. Min Act: -0.1700
Data Index: 550138 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.2768. Min Act: -0.1700
Data Index: 4781640 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.2143. Min Act: -0.1700
Data Index: 6522989 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.2143. Min Act: -0.1700
Data Index: 636580 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1830. Min Act: -0.1700
Data Index: 5101713 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1830. Min Act: -0.1700
Data Index: 8325415 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1830. Min Act: -0.1700
Data Index: 1983237 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1830. Min Act: -0.1700
Data Index: 7220117 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1830. Min Act: -0.1700
Data Index: 7895049 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1205. Min Act: -0.1700
Data Index: 4574947 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1205. Min Act: -0.1700
Data Index: 2171406 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1205. Min Act: -0.1700
Data Index: 3309902 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.0893. Min Act: -0.1700
Data Index: 7068650 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.0893. Min Act: -0.1700
Data Index: 7807040 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.1205. Min Act: -0.1700
Data Index: 5371392 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.0893. Min Act: -0.1700
Data Index: 4615033 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.0580. Min Act: -0.1700
Data Index: 4777399 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.0580. Min Act: -0.1700
Data Index: 2926434 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3705. Min Range: -6.3705
Max Act: 6.0580. Min Act: -0.1700
Data Index: 1783412 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3705. Min Range: -6.3705
Max Act: 5.9955. Min Act: -0.1700
Data Index: 4087787 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #19