Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3251 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.9430. Min Act: -0.1700
Data Index: 8144519 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.6617. Min Act: -0.1700
Data Index: 3415645 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.6304. Min Act: -0.1700
Data Index: 3685336 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.5054. Min Act: -0.1700
Data Index: 4016062 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.5054. Min Act: -0.1700
Data Index: 592125 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.4429. Min Act: -0.1700
Data Index: 8071795 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.4429. Min Act: -0.1700
Data Index: 4095783 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.4429. Min Act: -0.1700
Data Index: 4980945 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3804. Min Act: -0.1700
Data Index: 8668775 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3804. Min Act: -0.1700
Data Index: 7709418 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.4117. Min Act: -0.1700
Data Index: 929233 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3804. Min Act: -0.1700
Data Index: 1923666 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3804. Min Act: -0.1700
Data Index: 347454 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3492. Min Act: -0.1700
Data Index: 6697014 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3492. Min Act: -0.1700
Data Index: 8655765 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3492. Min Act: -0.1700
Data Index: 5708111 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3179. Min Act: -0.1700
Data Index: 3846709 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3179. Min Act: -0.1700
Data Index: 1103202 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3179. Min Act: -0.1700
Data Index: 258528 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9430. Min Range: -4.9430
Max Act: 4.3179. Min Act: -0.1700
Data Index: 2023730 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #19