Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 137 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 18.2664. Min Range: -18.2664
Max Act: 18.2664. Min Act: -0.1700
Data Index: 1038637 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.8914. Min Act: -0.1700
Data Index: 7579589 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.3914. Min Act: -0.1700
Data Index: 8221479 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.5164. Min Act: -0.1700
Data Index: 2488010 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.2664. Min Act: -0.1700
Data Index: 3526267 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.2664. Min Act: -0.1700
Data Index: 5633985 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 8194329 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 6578967 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 7573228 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 3856745 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 2738925 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 471943 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 2069313 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 18.2664. Min Range: -18.2664
Max Act: 17.0164. Min Act: -0.1700
Data Index: 5648535 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 18.2664. Min Range: -18.2664
Max Act: 16.8914. Min Act: -0.1700
Data Index: 6861659 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 18.2664. Min Range: -18.2664
Max Act: 16.8914. Min Act: -0.1700
Data Index: 6466409 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 18.2664. Min Range: -18.2664
Max Act: 16.8914. Min Act: -0.1700
Data Index: 1399625 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 18.2664. Min Range: -18.2664
Max Act: 16.7664. Min Act: -0.1700
Data Index: 3585208 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 18.2664. Min Range: -18.2664
Max Act: 16.7664. Min Act: -0.1700
Data Index: 1922739 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 18.2664. Min Range: -18.2664
Max Act: 16.7664. Min Act: -0.1700
Data Index: 1579058 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #19