Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0373. Min Range: -8.0373
Max Act: 8.0373. Min Act: -0.1700
Data Index: 1926220 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0373. Min Range: -8.0373
Max Act: 8.0373. Min Act: -0.1700
Data Index: 6015934 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.9435. Min Act: -0.1700
Data Index: 2985137 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.8498. Min Act: -0.1700
Data Index: 2928607 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.8810. Min Act: -0.1700
Data Index: 2072072 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.7873. Min Act: -0.1700
Data Index: 3094959 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.7560. Min Act: -0.1700
Data Index: 6280882 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.7873. Min Act: -0.1700
Data Index: 5847487 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.7560. Min Act: -0.1700
Data Index: 7316079 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.6935. Min Act: -0.1700
Data Index: 1039347 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.6935. Min Act: -0.1700
Data Index: 6084999 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.6623. Min Act: -0.1700
Data Index: 343823 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.6310. Min Act: -0.1700
Data Index: 8049282 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.5998. Min Act: -0.1700
Data Index: 3213204 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.5998. Min Act: -0.1700
Data Index: 8275363 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.5685. Min Act: -0.1700
Data Index: 2352529 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.5685. Min Act: -0.1700
Data Index: 7376429 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.5373. Min Act: -0.1700
Data Index: 1648304 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.5373. Min Act: -0.1700
Data Index: 3146253 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0373. Min Range: -8.0373
Max Act: 7.5373. Min Act: -0.1700
Data Index: 458269 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19