Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4170 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.5451. Min Act: -0.1700
Data Index: 264768 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.3889. Min Act: -0.1700
Data Index: 2613730 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.3264. Min Act: -0.1700
Data Index: 7427809 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.3264. Min Act: -0.1700
Data Index: 7512685 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.2951. Min Act: -0.1700
Data Index: 3017514 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.2326. Min Act: -0.1700
Data Index: 5909701 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.2326. Min Act: -0.1700
Data Index: 1001788 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.2014. Min Act: -0.1700
Data Index: 2210556 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.2014. Min Act: -0.1700
Data Index: 3997432 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.2014. Min Act: -0.1700
Data Index: 5908559 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1389. Min Act: -0.1700
Data Index: 1214371 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1701. Min Act: -0.1700
Data Index: 5908355 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1389. Min Act: -0.1700
Data Index: 2599161 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1389. Min Act: -0.1700
Data Index: 5958011 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1076. Min Act: -0.1700
Data Index: 180512 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1076. Min Act: -0.1700
Data Index: 1930793 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.1076. Min Act: -0.1700
Data Index: 7178823 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0764. Min Act: -0.1700
Data Index: 7250640 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0764. Min Act: -0.1700
Data Index: 6698471 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5451. Min Range: -6.5451
Max Act: 6.0764. Min Act: -0.1700
Data Index: 5591996 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #19