Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2438 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.5740. Min Act: -0.1700
Data Index: 4396708 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.5115. Min Act: -0.1700
Data Index: 4033741 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.4490. Min Act: -0.1700
Data Index: 4432491 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.4490. Min Act: -0.1700
Data Index: 8600253 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.3865. Min Act: -0.1700
Data Index: 5029053 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.3240. Min Act: -0.1700
Data Index: 6421658 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.3240. Min Act: -0.1700
Data Index: 8313724 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.2303. Min Act: -0.1700
Data Index: 3957096 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1990. Min Act: -0.1700
Data Index: 3516441 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1678. Min Act: -0.1700
Data Index: 3267968 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1053. Min Act: -0.1700
Data Index: 1587532 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1365. Min Act: -0.1700
Data Index: 2672281 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1365. Min Act: -0.1700
Data Index: 3806989 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1053. Min Act: -0.1700
Data Index: 437215 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1365. Min Act: -0.1700
Data Index: 2578221 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1365. Min Act: -0.1700
Data Index: 8022454 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1053. Min Act: -0.1700
Data Index: 1654551 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1053. Min Act: -0.1700
Data Index: 7684808 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.1053. Min Act: -0.1700
Data Index: 5117383 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5740. Min Range: -6.5740
Max Act: 6.0740. Min Act: -0.1700
Data Index: 5575172 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #19