Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1444 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.5423. Min Act: -0.1700
Data Index: 1038318 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4797. Min Act: -0.1700
Data Index: 6922673 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4640. Min Act: -0.1700
Data Index: 7989230 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4484. Min Act: -0.1700
Data Index: 4007465 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4640. Min Act: -0.1700
Data Index: 1572246 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4484. Min Act: -0.1700
Data Index: 7941535 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4170. Min Act: -0.1700
Data Index: 22385 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4170. Min Act: -0.1700
Data Index: 4276010 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4170. Min Act: -0.1700
Data Index: 3422144 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4484. Min Act: -0.1700
Data Index: 99532 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.3857. Min Act: -0.1700
Data Index: 7948913 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4170. Min Act: -0.1700
Data Index: 8370443 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4170. Min Act: -0.1700
Data Index: 680580 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.3857. Min Act: -0.1700
Data Index: 3757714 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.3857. Min Act: -0.1700
Data Index: 6750489 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4484. Min Act: -0.1700
Data Index: 6136634 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.4013. Min Act: -0.1700
Data Index: 5274891 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.3857. Min Act: -0.1700
Data Index: 4782046 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.3857. Min Act: -0.1700
Data Index: 360246 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5423. Min Range: -3.5423
Max Act: 3.3543. Min Act: -0.1700
Data Index: 4884911 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #19