Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6037 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.8708. Min Act: -0.1700
Data Index: 3858744 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.7771. Min Act: -0.1700
Data Index: 6272764 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.7458. Min Act: -0.1700
Data Index: 4380667 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.7458. Min Act: -0.1700
Data Index: 2802668 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.7146. Min Act: -0.1700
Data Index: 4512672 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.7146. Min Act: -0.1700
Data Index: 2531457 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.6833. Min Act: -0.1700
Data Index: 164679 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.6521. Min Act: -0.1700
Data Index: 2325081 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.6521. Min Act: -0.1700
Data Index: 1799488 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5896. Min Act: -0.1700
Data Index: 166978 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5896. Min Act: -0.1700
Data Index: 8449714 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5583. Min Act: -0.1700
Data Index: 7536589 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5896. Min Act: -0.1700
Data Index: 5577268 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5583. Min Act: -0.1700
Data Index: 5664195 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5583. Min Act: -0.1700
Data Index: 8131082 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5271. Min Act: -0.1700
Data Index: 5747025 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.5271. Min Act: -0.1700
Data Index: 4432364 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.4958. Min Act: -0.1700
Data Index: 605803 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.4958. Min Act: -0.1700
Data Index: 7103657 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8708. Min Range: -6.8708
Max Act: 6.4958. Min Act: -0.1700
Data Index: 5892260 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #19