Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3525 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1997. Min Range: -6.1997
Max Act: 6.1997. Min Act: -0.1700
Data Index: 3954245 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1997. Min Range: -6.1997
Max Act: 6.0122. Min Act: -0.1700
Data Index: 8322878 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.8559. Min Act: -0.1700
Data Index: 514361 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.8559. Min Act: -0.1700
Data Index: 6032540 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6997. Min Act: -0.1700
Data Index: 635531 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6997. Min Act: -0.1700
Data Index: 1590997 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6997. Min Act: -0.1700
Data Index: 1994952 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6684. Min Act: -0.1700
Data Index: 8578618 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6684. Min Act: -0.1700
Data Index: 8628484 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6684. Min Act: -0.1700
Data Index: 3389370 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6684. Min Act: -0.1700
Data Index: 3506845 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6684. Min Act: -0.1700
Data Index: 2187315 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6372. Min Act: -0.1700
Data Index: 825265 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6372. Min Act: -0.1700
Data Index: 5532444 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6372. Min Act: -0.1700
Data Index: 7494951 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6372. Min Act: -0.1700
Data Index: 1931886 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6059. Min Act: -0.1700
Data Index: 5033206 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6059. Min Act: -0.1700
Data Index: 1496580 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.5747. Min Act: -0.1700
Data Index: 8217487 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1997. Min Range: -6.1997
Max Act: 5.6059. Min Act: -0.1700
Data Index: 1909756 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #19