Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5816 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.5373. Min Act: -0.1700
Data Index: 7884824 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.4123. Min Act: -0.1700
Data Index: 6417120 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.4123. Min Act: -0.1700
Data Index: 8463105 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.3811. Min Act: -0.1700
Data Index: 3899603 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.3811. Min Act: -0.1700
Data Index: 6297509 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.3498. Min Act: -0.1700
Data Index: 1709013 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.2561. Min Act: -0.1700
Data Index: 7019300 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.1311. Min Act: -0.1700
Data Index: 3764691 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.0686. Min Act: -0.1700
Data Index: 7528881 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.0998. Min Act: -0.1700
Data Index: 3608901 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.0998. Min Act: -0.1700
Data Index: 7954212 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.0373. Min Act: -0.1700
Data Index: 2972552 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.0061. Min Act: -0.1700
Data Index: 7258331 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.0061. Min Act: -0.1700
Data Index: 493506 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5373. Min Range: -6.5373
Max Act: 5.9436. Min Act: -0.1700
Data Index: 4960134 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5373. Min Range: -6.5373
Max Act: 6.0061. Min Act: -0.1700
Data Index: 7286400 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5373. Min Range: -6.5373
Max Act: 5.9436. Min Act: -0.1700
Data Index: 877778 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5373. Min Range: -6.5373
Max Act: 5.9123. Min Act: -0.1700
Data Index: 213925 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5373. Min Range: -6.5373
Max Act: 5.9436. Min Act: -0.1700
Data Index: 5693007 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5373. Min Range: -6.5373
Max Act: 5.9436. Min Act: -0.1700
Data Index: 7709043 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #19