Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3779 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0697. Min Range: -7.0697
Max Act: 7.0697. Min Act: -0.1700
Data Index: 748106 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.8197. Min Act: -0.1700
Data Index: 7555826 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.7572. Min Act: -0.1700
Data Index: 7050827 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.7572. Min Act: -0.1700
Data Index: 7136726 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.7572. Min Act: -0.1700
Data Index: 4902551 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.7259. Min Act: -0.1700
Data Index: 6203997 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.7259. Min Act: -0.1700
Data Index: 2849536 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.7259. Min Act: -0.1700
Data Index: 5839375 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6947. Min Act: -0.1700
Data Index: 1563040 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6947. Min Act: -0.1700
Data Index: 6606966 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6947. Min Act: -0.1700
Data Index: 3699277 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6634. Min Act: -0.1700
Data Index: 7887641 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6634. Min Act: -0.1700
Data Index: 6498642 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6634. Min Act: -0.1700
Data Index: 865005 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6947. Min Act: -0.1700
Data Index: 7507267 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6634. Min Act: -0.1700
Data Index: 8608662 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6634. Min Act: -0.1700
Data Index: 1860776 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6322. Min Act: -0.1700
Data Index: 5259826 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6322. Min Act: -0.1700
Data Index: 3780819 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0697. Min Range: -7.0697
Max Act: 6.6322. Min Act: -0.1700
Data Index: 2189249 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #19