Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2605 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0040. Min Range: -8.0040
Max Act: 8.0040. Min Act: -0.1700
Data Index: 6221279 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.9728. Min Act: -0.1700
Data Index: 1780415 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.9728. Min Act: -0.1700
Data Index: 1158730 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.9103. Min Act: -0.1700
Data Index: 3397376 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.9103. Min Act: -0.1700
Data Index: 6121796 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.9103. Min Act: -0.1700
Data Index: 5329534 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.7853. Min Act: -0.1700
Data Index: 8376309 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.7228. Min Act: -0.1700
Data Index: 2072801 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.7228. Min Act: -0.1700
Data Index: 6451123 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.6915. Min Act: -0.1700
Data Index: 3855342 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.6290. Min Act: -0.1700
Data Index: 5774650 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.6290. Min Act: -0.1700
Data Index: 5742224 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.6290. Min Act: -0.1700
Data Index: 8102212 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.6290. Min Act: -0.1700
Data Index: 2513746 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.6290. Min Act: -0.1700
Data Index: 5919655 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.5978. Min Act: -0.1700
Data Index: 7740238 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.5665. Min Act: -0.1700
Data Index: 7872988 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.5978. Min Act: -0.1700
Data Index: 7137691 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.5978. Min Act: -0.1700
Data Index: 6883994 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0040. Min Range: -8.0040
Max Act: 7.5665. Min Act: -0.1700
Data Index: 2822753 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #19