Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 340 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.4876. Min Act: -0.1700
Data Index: 6668929 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.4563. Min Act: -0.1700
Data Index: 5491544 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.4563. Min Act: -0.1700
Data Index: 7105127 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.3313. Min Act: -0.1700
Data Index: 3182445 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.2688. Min Act: -0.1700
Data Index: 2921485 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.2688. Min Act: -0.1700
Data Index: 728817 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.2376. Min Act: -0.1700
Data Index: 4979242 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.2376. Min Act: -0.1700
Data Index: 5143056 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.2063. Min Act: -0.1700
Data Index: 6743762 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.1751. Min Act: -0.1700
Data Index: 5863333 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.2063. Min Act: -0.1700
Data Index: 7732580 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.2063. Min Act: -0.1700
Data Index: 3394498 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.1751. Min Act: -0.1700
Data Index: 1471801 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.1438. Min Act: -0.1700
Data Index: 877949 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.1126. Min Act: -0.1700
Data Index: 66122 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0813. Min Act: -0.1700
Data Index: 3515187 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0501. Min Act: -0.1700
Data Index: 8040380 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0501. Min Act: -0.1700
Data Index: 1711009 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0501. Min Act: -0.1700
Data Index: 2293651 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4876. Min Range: -7.4876
Max Act: 7.0501. Min Act: -0.1700
Data Index: 7713798 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #19