Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3238 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.7417. Min Act: -0.1700
Data Index: 8829827 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.5230. Min Act: -0.1700
Data Index: 7925370 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.4917. Min Act: -0.1700
Data Index: 5756427 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.4917. Min Act: -0.1700
Data Index: 7037737 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.4917. Min Act: -0.1700
Data Index: 1373125 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.4605. Min Act: -0.1700
Data Index: 7432461 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.4292. Min Act: -0.1700
Data Index: 5149632 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3980. Min Act: -0.1700
Data Index: 6556649 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3980. Min Act: -0.1700
Data Index: 484789 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3980. Min Act: -0.1700
Data Index: 2796397 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3667. Min Act: -0.1700
Data Index: 6608502 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3355. Min Act: -0.1700
Data Index: 5268964 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3042. Min Act: -0.1700
Data Index: 6801645 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3042. Min Act: -0.1700
Data Index: 4250795 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3042. Min Act: -0.1700
Data Index: 5968918 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3042. Min Act: -0.1700
Data Index: 6766740 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.3042. Min Act: -0.1700
Data Index: 8385704 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.2730. Min Act: -0.1700
Data Index: 5384097 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.2730. Min Act: -0.1700
Data Index: 5425326 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.2730. Min Act: -0.1700
Data Index: 6395331 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #19