Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2431 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0733. Min Range: -9.0733
Max Act: 9.0733. Min Act: -0.1700
Data Index: 5586120 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.8858. Min Act: -0.1700
Data Index: 2580036 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.8233. Min Act: -0.1700
Data Index: 7701679 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.6983. Min Act: -0.1700
Data Index: 1856806 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.6358. Min Act: -0.1700
Data Index: 6337633 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.6358. Min Act: -0.1700
Data Index: 7021168 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.6358. Min Act: -0.1700
Data Index: 8243811 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.5108. Min Act: -0.1700
Data Index: 7401788 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.4483. Min Act: -0.1700
Data Index: 4632495 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.4483. Min Act: -0.1700
Data Index: 6905066 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.4483. Min Act: -0.1700
Data Index: 3358721 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.3858. Min Act: -0.1700
Data Index: 3000830 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.3858. Min Act: -0.1700
Data Index: 1906011 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.3233. Min Act: -0.1700
Data Index: 3939421 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.3858. Min Act: -0.1700
Data Index: 8263210 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.3233. Min Act: -0.1700
Data Index: 8158634 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.3233. Min Act: -0.1700
Data Index: 7587014 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.2608. Min Act: -0.1700
Data Index: 1765838 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.2608. Min Act: -0.1700
Data Index: 3469859 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0733. Min Range: -9.0733
Max Act: 8.2608. Min Act: -0.1700
Data Index: 4961313 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19