Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4949 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.8913. Min Act: -0.1700
Data Index: 4019652 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.7193. Min Act: -0.1700
Data Index: 1062257 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.7036. Min Act: -0.1700
Data Index: 5386494 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.6567. Min Act: -0.1700
Data Index: 10521 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.5941. Min Act: -0.1700
Data Index: 4668995 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.5785. Min Act: -0.1700
Data Index: 1736768 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.5628. Min Act: -0.1700
Data Index: 16654 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.5315. Min Act: -0.1700
Data Index: 2437413 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.5002. Min Act: -0.1700
Data Index: 2987906 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4845. Min Act: -0.1700
Data Index: 4668439 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4532. Min Act: -0.1700
Data Index: 437771 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4688. Min Act: -0.1700
Data Index: 538897 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4845. Min Act: -0.1700
Data Index: 8425883 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4532. Min Act: -0.1700
Data Index: 3166947 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4375. Min Act: -0.1700
Data Index: 5408566 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4062. Min Act: -0.1700
Data Index: 4285516 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4218. Min Act: -0.1700
Data Index: 4858802 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4218. Min Act: -0.1700
Data Index: 4679298 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4375. Min Act: -0.1700
Data Index: 972833 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8913. Min Range: -3.8913
Max Act: 3.4218. Min Act: -0.1700
Data Index: 3121730 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #19