Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1644 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.6870. Min Act: -0.1700
Data Index: 8477011 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.6558. Min Act: -0.1700
Data Index: 723769 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.6245. Min Act: -0.1700
Data Index: 1790288 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.5620. Min Act: -0.1700
Data Index: 5246455 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.4058. Min Act: -0.1700
Data Index: 825337 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.4058. Min Act: -0.1700
Data Index: 1960993 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.3120. Min Act: -0.1700
Data Index: 1604529 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2808. Min Act: -0.1700
Data Index: 6070534 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2808. Min Act: -0.1700
Data Index: 923243 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2808. Min Act: -0.1700
Data Index: 4055220 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2808. Min Act: -0.1700
Data Index: 417056 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2495. Min Act: -0.1700
Data Index: 3620424 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2495. Min Act: -0.1700
Data Index: 6388924 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2495. Min Act: -0.1700
Data Index: 7587133 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2495. Min Act: -0.1700
Data Index: 2781459 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2495. Min Act: -0.1700
Data Index: 8555436 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.1870. Min Act: -0.1700
Data Index: 1818914 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.2183. Min Act: -0.1700
Data Index: 6145081 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.1870. Min Act: -0.1700
Data Index: 3572565 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6870. Min Range: -4.6870
Max Act: 4.1558. Min Act: -0.1700
Data Index: 846503 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #19