Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 75 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2947. Min Act: -0.1700
Data Index: 4564779 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2634. Min Act: -0.1700
Data Index: 2750468 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.2009. Min Act: -0.1700
Data Index: 847099 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1697. Min Act: -0.1700
Data Index: 5197218 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1697. Min Act: -0.1700
Data Index: 4630949 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1697. Min Act: -0.1700
Data Index: 6113599 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1384. Min Act: -0.1700
Data Index: 5112191 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1384. Min Act: -0.1700
Data Index: 817759 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1071. Min Act: -0.1700
Data Index: 6312169 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1071. Min Act: -0.1700
Data Index: 3287808 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1071. Min Act: -0.1700
Data Index: 8647589 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1071. Min Act: -0.1700
Data Index: 7485510 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.1071. Min Act: -0.1700
Data Index: 8459627 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 2536118 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 2997569 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 7686602 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 7104978 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0759. Min Act: -0.1700
Data Index: 6137291 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0446. Min Act: -0.1700
Data Index: 6719215 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2947. Min Range: -4.2947
Max Act: 4.0446. Min Act: -0.1700
Data Index: 270014 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #19