Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 316 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.1842. Min Act: -0.1700
Data Index: 2352584 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.1842. Min Act: -0.1700
Data Index: 3481864 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.1217. Min Act: -0.1700
Data Index: 6682491 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.1217. Min Act: -0.1700
Data Index: 1243380 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0904. Min Act: -0.1700
Data Index: 539913 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0904. Min Act: -0.1700
Data Index: 3446657 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 4991207 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0592. Min Act: -0.1700
Data Index: 3272384 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 4117792 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 6053661 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 5220074 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 3155460 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 8561075 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 7322589 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1842. Min Range: -4.1842
Max Act: 3.9966. Min Act: -0.1700
Data Index: 6931938 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1842. Min Range: -4.1842
Max Act: 4.0279. Min Act: -0.1700
Data Index: 1698778 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1842. Min Range: -4.1842
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7645496 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1842. Min Range: -4.1842
Max Act: 3.9966. Min Act: -0.1700
Data Index: 7257232 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1842. Min Range: -4.1842
Max Act: 3.9654. Min Act: -0.1700
Data Index: 4863311 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1842. Min Range: -4.1842
Max Act: 3.9654. Min Act: -0.1700
Data Index: 3631740 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19