Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2919 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1051. Min Range: -9.1051
Max Act: 9.1051. Min Act: -0.1700
Data Index: 6194238 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.9801. Min Act: -0.1700
Data Index: 6794185 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.8551. Min Act: -0.1700
Data Index: 5245905 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.7301. Min Act: -0.1700
Data Index: 2687507 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.7301. Min Act: -0.1700
Data Index: 1421681 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.7301. Min Act: -0.1700
Data Index: 4694842 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 306541 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 6192735 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.7301. Min Act: -0.1700
Data Index: 7714443 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.7301. Min Act: -0.1700
Data Index: 1250745 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 2739290 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 4424455 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 4621718 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 366789 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 7724083 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6051. Min Act: -0.1700
Data Index: 2921372 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6051. Min Act: -0.1700
Data Index: 8758754 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 2709626 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6676. Min Act: -0.1700
Data Index: 6992502 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1051. Min Range: -9.1051
Max Act: 8.6051. Min Act: -0.1700
Data Index: 5298384 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #19