Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6307 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.8666. Min Act: -0.1700
Data Index: 3578802 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.7711. Min Act: -0.1700
Data Index: 7527251 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.7711. Min Act: -0.1700
Data Index: 1807668 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.7551. Min Act: -0.1700
Data Index: 6717822 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.7551. Min Act: -0.1700
Data Index: 8199693 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.7551. Min Act: -0.1700
Data Index: 6717823 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.7551. Min Act: -0.1700
Data Index: 3547423 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.7711. Min Act: -0.1700
Data Index: 4263335 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6912. Min Act: -0.1700
Data Index: 3923977 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6912. Min Act: -0.1700
Data Index: 5976173 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6912. Min Act: -0.1700
Data Index: 6985108 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6592. Min Act: -0.1700
Data Index: 5162072 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6592. Min Act: -0.1700
Data Index: 348186 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6592. Min Act: -0.1700
Data Index: 2401282 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6431. Min Act: -0.1700
Data Index: 1676926 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6431. Min Act: -0.1700
Data Index: 8464827 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6431. Min Act: -0.1700
Data Index: 512119 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6270. Min Act: -0.1700
Data Index: 5133679 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6270. Min Act: -0.1700
Data Index: 6085479 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8666. Min Range: -2.8666
Max Act: 2.6270. Min Act: -0.1700
Data Index: 1316322 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #19