Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3573 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.1525. Min Act: -0.1700
Data Index: 5008352 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0900. Min Act: -0.1700
Data Index: 7279539 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0900. Min Act: -0.1700
Data Index: 2421753 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0587. Min Act: -0.1700
Data Index: 8225345 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7295016 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0587. Min Act: -0.1700
Data Index: 7301330 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0587. Min Act: -0.1700
Data Index: 4957057 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 1678441 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 4976183 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7099242 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 5679496 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 5179094 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 582472 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 4664741 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 3078794 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 7481861 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1525. Min Range: -5.1525
Max Act: 5.0275. Min Act: -0.1700
Data Index: 1308358 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1525. Min Range: -5.1525
Max Act: 4.9962. Min Act: -0.1700
Data Index: 4167685 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1525. Min Range: -5.1525
Max Act: 4.9962. Min Act: -0.1700
Data Index: 1152265 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1525. Min Range: -5.1525
Max Act: 4.9962. Min Act: -0.1700
Data Index: 4861558 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19