Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2664 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3413. Min Range: -10.3413
Max Act: 10.3413. Min Act: -0.1700
Data Index: 8240014 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3413. Min Range: -10.3413
Max Act: 10.3413. Min Act: -0.1700
Data Index: 4019417 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3413. Min Range: -10.3413
Max Act: 10.0913. Min Act: -0.1700
Data Index: 6335442 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3413. Min Range: -10.3413
Max Act: 10.0288. Min Act: -0.1700
Data Index: 4174884 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.9663. Min Act: -0.1700
Data Index: 6224377 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.9663. Min Act: -0.1700
Data Index: 3646562 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.9663. Min Act: -0.1700
Data Index: 3416993 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.9663. Min Act: -0.1700
Data Index: 8631349 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.9038. Min Act: -0.1700
Data Index: 5982269 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.8413. Min Act: -0.1700
Data Index: 1758790 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.8413. Min Act: -0.1700
Data Index: 5525630 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.7788. Min Act: -0.1700
Data Index: 4313085 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.7788. Min Act: -0.1700
Data Index: 7641986 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.7788. Min Act: -0.1700
Data Index: 3185981 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.7788. Min Act: -0.1700
Data Index: 7598317 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.7788. Min Act: -0.1700
Data Index: 5627647 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.6538. Min Act: -0.1700
Data Index: 485347 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.7163. Min Act: -0.1700
Data Index: 5352645 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.6538. Min Act: -0.1700
Data Index: 3860439 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3413. Min Range: -10.3413
Max Act: 9.5913. Min Act: -0.1700
Data Index: 2093283 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #19