Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3336 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0308. Min Range: -8.0308
Max Act: 8.0308. Min Act: -0.1700
Data Index: 966335 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.9058. Min Act: -0.1700
Data Index: 1632002 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.7183. Min Act: -0.1700
Data Index: 7977240 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.6558. Min Act: -0.1700
Data Index: 6308185 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.6558. Min Act: -0.1700
Data Index: 2529821 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5933. Min Act: -0.1700
Data Index: 6453933 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5620. Min Act: -0.1700
Data Index: 7901795 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5620. Min Act: -0.1700
Data Index: 6522175 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5620. Min Act: -0.1700
Data Index: 2195535 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5308. Min Act: -0.1700
Data Index: 2466820 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5620. Min Act: -0.1700
Data Index: 6930941 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.5308. Min Act: -0.1700
Data Index: 4732048 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4995. Min Act: -0.1700
Data Index: 6697565 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4683. Min Act: -0.1700
Data Index: 5663854 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4995. Min Act: -0.1700
Data Index: 3197952 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4683. Min Act: -0.1700
Data Index: 2692672 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4683. Min Act: -0.1700
Data Index: 4022791 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4058. Min Act: -0.1700
Data Index: 3866311 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4370. Min Act: -0.1700
Data Index: 3990379 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0308. Min Range: -8.0308
Max Act: 7.4683. Min Act: -0.1700
Data Index: 3218211 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19