Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2996 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0268. Min Range: -6.0268
Max Act: 6.0268. Min Act: -0.1700
Data Index: 8335624 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.9331. Min Act: -0.1700
Data Index: 3357218 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.8706. Min Act: -0.1700
Data Index: 462599 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.8393. Min Act: -0.1700
Data Index: 4765984 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.8393. Min Act: -0.1700
Data Index: 5464521 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.7456. Min Act: -0.1700
Data Index: 1885593 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.7456. Min Act: -0.1700
Data Index: 3747362 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.7143. Min Act: -0.1700
Data Index: 7031007 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.7143. Min Act: -0.1700
Data Index: 135894 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6831. Min Act: -0.1700
Data Index: 551806 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6831. Min Act: -0.1700
Data Index: 3582063 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6831. Min Act: -0.1700
Data Index: 1389345 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6518. Min Act: -0.1700
Data Index: 3653034 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6518. Min Act: -0.1700
Data Index: 7296937 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6206. Min Act: -0.1700
Data Index: 4946504 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6518. Min Act: -0.1700
Data Index: 2175326 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.5893. Min Act: -0.1700
Data Index: 4528651 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6206. Min Act: -0.1700
Data Index: 2643316 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6206. Min Act: -0.1700
Data Index: 335271 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0268. Min Range: -6.0268
Max Act: 5.6206. Min Act: -0.1700
Data Index: 5630121 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19