Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4568 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.9365. Min Act: -0.1700
Data Index: 7844993 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.8115. Min Act: -0.1700
Data Index: 7334559 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.7490. Min Act: -0.1700
Data Index: 293318 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.6865. Min Act: -0.1700
Data Index: 7802885 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.6865. Min Act: -0.1700
Data Index: 646946 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.6865. Min Act: -0.1700
Data Index: 2299968 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.6240. Min Act: -0.1700
Data Index: 578871 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.6240. Min Act: -0.1700
Data Index: 650607 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.5615. Min Act: -0.1700
Data Index: 704695 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.5615. Min Act: -0.1700
Data Index: 8118367 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4990. Min Act: -0.1700
Data Index: 6383198 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4990. Min Act: -0.1700
Data Index: 4063613 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.3740. Min Act: -0.1700
Data Index: 7248764 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4365. Min Act: -0.1700
Data Index: 7295074 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4365. Min Act: -0.1700
Data Index: 4113383 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4365. Min Act: -0.1700
Data Index: 6386901 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4365. Min Act: -0.1700
Data Index: 7462041 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4365. Min Act: -0.1700
Data Index: 2864064 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.3740. Min Act: -0.1700
Data Index: 6589284 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9365. Min Range: -9.9365
Max Act: 9.4365. Min Act: -0.1700
Data Index: 6102661 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19