Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3092 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.9403. Min Act: -0.1700
Data Index: 3192887 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.9403. Min Act: -0.1700
Data Index: 3192889 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.9244. Min Act: -0.1700
Data Index: 3192888 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.9086. Min Act: -0.1700
Data Index: 3192886 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.8451. Min Act: -0.1700
Data Index: 7721644 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.7495. Min Act: -0.1698
Data Index: 8036031 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.7336. Min Act: -0.1700
Data Index: 1390867 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.7495. Min Act: -0.1700
Data Index: 3537631 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.7176. Min Act: -0.1700
Data Index: 3805292 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.7016. Min Act: -0.1700
Data Index: 5155310 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6856. Min Act: -0.1700
Data Index: 3577661 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6535. Min Act: -0.1700
Data Index: 2235297 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6696. Min Act: -0.1700
Data Index: 4593385 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6696. Min Act: -0.1700
Data Index: 4916125 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6696. Min Act: -0.1700
Data Index: 5080329 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6375. Min Act: -0.1700
Data Index: 8224263 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6696. Min Act: -0.1700
Data Index: 5784603 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6535. Min Act: -0.1700
Data Index: 1248902 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6214. Min Act: -0.1700
Data Index: 3649759 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9403. Min Range: -2.9403
Max Act: 2.6375. Min Act: -0.1700
Data Index: 3797693 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19