Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1066 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.9076. Min Act: -0.1700
Data Index: 7780656 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.9076. Min Act: -0.1700
Data Index: 3617606 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.7201. Min Act: -0.1700
Data Index: 4342308 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.5014. Min Act: -0.1700
Data Index: 7304260 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.4076. Min Act: -0.1700
Data Index: 3994157 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.3139. Min Act: -0.1700
Data Index: 2210547 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.3451. Min Act: -0.1700
Data Index: 1972898 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.3139. Min Act: -0.1700
Data Index: 1873050 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.2514. Min Act: -0.1700
Data Index: 7737979 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.2201. Min Act: -0.1700
Data Index: 5039182 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.1889. Min Act: -0.1700
Data Index: 5112302 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.2201. Min Act: -0.1700
Data Index: 5139766 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.1576. Min Act: -0.1700
Data Index: 828606 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.1576. Min Act: -0.1700
Data Index: 5080328 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.0639. Min Act: -0.1700
Data Index: 3892757 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.1264. Min Act: -0.1700
Data Index: 2026888 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.0951. Min Act: -0.1700
Data Index: 3369907 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.0639. Min Act: -0.1700
Data Index: 8056247 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.0639. Min Act: -0.1700
Data Index: 1014855 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9076. Min Range: -7.9076
Max Act: 7.0014. Min Act: -0.1700
Data Index: 64661 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19