Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2016 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.1090. Min Act: -0.1700
Data Index: 6100614 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.1090. Min Act: -0.1700
Data Index: 5798147 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.1090. Min Act: -0.1700
Data Index: 3491886 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.1090. Min Act: -0.1700
Data Index: 1843593 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.1090. Min Act: -0.1700
Data Index: 1075397 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0777. Min Act: -0.1700
Data Index: 6549145 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0777. Min Act: -0.1700
Data Index: 5222140 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0777. Min Act: -0.1700
Data Index: 4315547 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0777. Min Act: -0.1700
Data Index: 8116508 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.1090. Min Act: -0.1700
Data Index: 6286767 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0777. Min Act: -0.1700
Data Index: 7795117 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0465. Min Act: -0.1700
Data Index: 6872925 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0465. Min Act: -0.1700
Data Index: 5689803 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0152. Min Act: -0.1700
Data Index: 4232292 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1090. Min Range: -6.1090
Max Act: 5.9840. Min Act: -0.1700
Data Index: 4846359 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1090. Min Range: -6.1090
Max Act: 6.0152. Min Act: -0.1700
Data Index: 3640894 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1090. Min Range: -6.1090
Max Act: 5.9840. Min Act: -0.1700
Data Index: 1576423 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1090. Min Range: -6.1090
Max Act: 5.9840. Min Act: -0.1700
Data Index: 4910871 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1090. Min Range: -6.1090
Max Act: 5.9527. Min Act: -0.1700
Data Index: 8455727 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1090. Min Range: -6.1090
Max Act: 5.9840. Min Act: -0.1700
Data Index: 8638452 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #19