Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2622 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2010. Min Range: -7.2010
Max Act: 7.2010. Min Act: -0.1700
Data Index: 6682389 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2010. Min Range: -7.2010
Max Act: 7.2010. Min Act: -0.1700
Data Index: 2368114 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2010. Min Range: -7.2010
Max Act: 7.1073. Min Act: -0.1700
Data Index: 3340115 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2010. Min Range: -7.2010
Max Act: 7.0135. Min Act: -0.1700
Data Index: 2195787 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.9198. Min Act: -0.1700
Data Index: 3092062 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.9198. Min Act: -0.1700
Data Index: 3119764 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7948. Min Act: -0.1700
Data Index: 6497419 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7635. Min Act: -0.1700
Data Index: 5857163 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7323. Min Act: -0.1700
Data Index: 5429636 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7323. Min Act: -0.1700
Data Index: 7022696 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7635. Min Act: -0.1700
Data Index: 4734613 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7323. Min Act: -0.1700
Data Index: 5214569 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7010. Min Act: -0.1700
Data Index: 2675487 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7010. Min Act: -0.1700
Data Index: 3290702 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7010. Min Act: -0.1700
Data Index: 3658946 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.6698. Min Act: -0.1700
Data Index: 3167104 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.6698. Min Act: -0.1700
Data Index: 1014886 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.7010. Min Act: -0.1700
Data Index: 4542154 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.6385. Min Act: -0.1700
Data Index: 317092 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2010. Min Range: -7.2010
Max Act: 6.6698. Min Act: -0.1700
Data Index: 4362845 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #19