Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3122 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.4042. Min Act: -0.1700
Data Index: 729509 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.3885. Min Act: -0.1700
Data Index: 414645 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2787. Min Act: -0.1700
Data Index: 5693655 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2787. Min Act: -0.1700
Data Index: 1966390 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2787. Min Act: -0.1700
Data Index: 6765368 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2787. Min Act: -0.1700
Data Index: 8370106 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2787. Min Act: -0.1700
Data Index: 1604943 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2630. Min Act: -0.1700
Data Index: 4950732 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2473. Min Act: -0.1700
Data Index: 2452655 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2473. Min Act: -0.1700
Data Index: 777359 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2315. Min Act: -0.1700
Data Index: 5925523 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2630. Min Act: -0.1700
Data Index: 2094994 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2473. Min Act: -0.1700
Data Index: 3978108 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2315. Min Act: -0.1700
Data Index: 523004 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2315. Min Act: -0.1700
Data Index: 279788 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2315. Min Act: -0.1700
Data Index: 1881877 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2158. Min Act: -0.1700
Data Index: 755539 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2158. Min Act: -0.1700
Data Index: 3814176 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2001. Min Act: -0.1700
Data Index: 1260458 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4042. Min Range: -3.4042
Max Act: 3.2001. Min Act: -0.1700
Data Index: 211262 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19