Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2129 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.2525. Min Act: -0.1700
Data Index: 6836552 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1587. Min Act: -0.1700
Data Index: 611682 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1587. Min Act: -0.1700
Data Index: 2709561 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.1275. Min Act: -0.1700
Data Index: 6452949 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0962. Min Act: -0.1700
Data Index: 4351341 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0962. Min Act: -0.1700
Data Index: 3384329 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0962. Min Act: -0.1700
Data Index: 7000297 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0962. Min Act: -0.1700
Data Index: 2764503 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0962. Min Act: -0.1700
Data Index: 6393841 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 8610124 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 8551692 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 667832 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 1824227 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 6814117 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0650. Min Act: -0.1700
Data Index: 3001032 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7036766 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0025. Min Act: -0.1700
Data Index: 7342104 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 7367607 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 8195177 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2525. Min Range: -5.2525
Max Act: 5.0337. Min Act: -0.1700
Data Index: 1710902 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #19