Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3516 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 14.1323. Min Range: -14.1323
Max Act: 14.1323. Min Act: -0.1700
Data Index: 6553723 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.9448. Min Act: -0.1700
Data Index: 3704605 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.8823. Min Act: -0.1700
Data Index: 3797059 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.8823. Min Act: -0.1700
Data Index: 7755659 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.8198. Min Act: -0.1700
Data Index: 6719548 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.6948. Min Act: -0.1700
Data Index: 6648523 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.6323. Min Act: -0.1700
Data Index: 1251698 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.6323. Min Act: -0.1700
Data Index: 1584692 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.6323. Min Act: -0.1700
Data Index: 5007870 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.5698. Min Act: -0.1700
Data Index: 5084451 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.5698. Min Act: -0.1700
Data Index: 5677652 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.6323. Min Act: -0.1700
Data Index: 1525255 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.5698. Min Act: -0.1700
Data Index: 7042504 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.4448. Min Act: -0.1700
Data Index: 5273859 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.3823. Min Act: -0.1700
Data Index: 8549806 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.3823. Min Act: -0.1700
Data Index: 2922101 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.3823. Min Act: -0.1700
Data Index: 6944556 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.3823. Min Act: -0.1700
Data Index: 3472671 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.3198. Min Act: -0.1700
Data Index: 4145739 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 14.1323. Min Range: -14.1323
Max Act: 13.3823. Min Act: -0.1700
Data Index: 3693890 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19