Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2703 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.6368. Min Act: -0.1700
Data Index: 5103954 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.5743. Min Act: -0.1700
Data Index: 697475 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.3868. Min Act: -0.1700
Data Index: 5103955 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.1056. Min Act: -0.1700
Data Index: 5231488 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.0743. Min Act: -0.1700
Data Index: 2164682 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.1368. Min Act: -0.1700
Data Index: 3497808 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.1056. Min Act: -0.1700
Data Index: 5671865 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.0431. Min Act: -0.1700
Data Index: 6415187 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.0118. Min Act: -0.1700
Data Index: 2554798 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6368. Min Range: -7.6368
Max Act: 7.0118. Min Act: -0.1700
Data Index: 3855288 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9806. Min Act: -0.1700
Data Index: 3134399 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9806. Min Act: -0.1700
Data Index: 7983602 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9806. Min Act: -0.1700
Data Index: 4670983 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9493. Min Act: -0.1700
Data Index: 8022065 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9806. Min Act: -0.1700
Data Index: 6318205 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9806. Min Act: -0.1700
Data Index: 1069542 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9493. Min Act: -0.1700
Data Index: 7395371 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9181. Min Act: -0.1700
Data Index: 6483415 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9493. Min Act: -0.1700
Data Index: 85639 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6368. Min Range: -7.6368
Max Act: 6.9181. Min Act: -0.1700
Data Index: 3103174 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19