Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3708 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.5893. Min Act: -0.1700
Data Index: 3651651 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.4643. Min Act: -0.1700
Data Index: 6076086 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.4018. Min Act: -0.1700
Data Index: 3061984 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.4018. Min Act: -0.1700
Data Index: 6093398 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.3393. Min Act: -0.1700
Data Index: 1632901 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.3393. Min Act: -0.1700
Data Index: 7061581 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.1830. Min Act: -0.1700
Data Index: 5696388 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.2455. Min Act: -0.1700
Data Index: 1268998 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.1830. Min Act: -0.1700
Data Index: 8031532 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.1830. Min Act: -0.1700
Data Index: 2917700 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.1205. Min Act: -0.1700
Data Index: 8234075 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.1830. Min Act: -0.1700
Data Index: 2871356 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.1518. Min Act: -0.1700
Data Index: 371792 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.1205. Min Act: -0.1700
Data Index: 8803787 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.0893. Min Act: -0.1700
Data Index: 6766113 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.0580. Min Act: -0.1700
Data Index: 8187691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.0268. Min Act: -0.1700
Data Index: 3169375 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.0268. Min Act: -0.1700
Data Index: 5979744 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.0268. Min Act: -0.1700
Data Index: 7355715 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5893. Min Range: -7.5893
Max Act: 7.0580. Min Act: -0.1700
Data Index: 3180234 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19