Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3188 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.4451. Min Act: -0.1700
Data Index: 6211587 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.2264. Min Act: -0.1700
Data Index: 5668084 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.1951. Min Act: -0.1700
Data Index: 2589343 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.1639. Min Act: -0.1700
Data Index: 103559 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.1326. Min Act: -0.1700
Data Index: 2074673 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.1014. Min Act: -0.1700
Data Index: 2901932 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.0701. Min Act: -0.1700
Data Index: 1420524 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.0389. Min Act: -0.1700
Data Index: 866273 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4451. Min Range: -7.4451
Max Act: 7.0076. Min Act: -0.1700
Data Index: 3665319 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.9451. Min Act: -0.1700
Data Index: 2413557 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.9451. Min Act: -0.1700
Data Index: 3549824 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.9139. Min Act: -0.1700
Data Index: 5142946 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.8826. Min Act: -0.1700
Data Index: 6814322 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.9139. Min Act: -0.1700
Data Index: 7645677 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.8201. Min Act: -0.1700
Data Index: 8028846 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.8201. Min Act: -0.1700
Data Index: 6154730 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.8201. Min Act: -0.1700
Data Index: 7239089 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.8201. Min Act: -0.1700
Data Index: 4267189 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.7576. Min Act: -0.1700
Data Index: 5318878 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4451. Min Range: -7.4451
Max Act: 6.7576. Min Act: -0.1700
Data Index: 4130002 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19