Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2484 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2607. Min Range: -6.2607
Max Act: 6.2607. Min Act: -0.1700
Data Index: 4202135 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2607. Min Range: -6.2607
Max Act: 6.2295. Min Act: -0.1700
Data Index: 2376303 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2607. Min Range: -6.2607
Max Act: 6.0420. Min Act: -0.1700
Data Index: 4142471 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2607. Min Range: -6.2607
Max Act: 6.0420. Min Act: -0.1700
Data Index: 6919962 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2607. Min Range: -6.2607
Max Act: 6.0107. Min Act: -0.1700
Data Index: 8815594 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.9795. Min Act: -0.1700
Data Index: 4684479 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.9482. Min Act: -0.1700
Data Index: 7883908 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.9170. Min Act: -0.1700
Data Index: 4051281 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8857. Min Act: -0.1700
Data Index: 4708303 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.9170. Min Act: -0.1700
Data Index: 1050302 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8545. Min Act: -0.1700
Data Index: 2551225 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8545. Min Act: -0.1700
Data Index: 782323 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8232. Min Act: -0.1700
Data Index: 166837 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8232. Min Act: -0.1700
Data Index: 4447013 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8232. Min Act: -0.1700
Data Index: 4742723 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8232. Min Act: -0.1700
Data Index: 1287929 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.8232. Min Act: -0.1700
Data Index: 7912793 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.7607. Min Act: -0.1700
Data Index: 109194 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.7607. Min Act: -0.1700
Data Index: 2387895 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2607. Min Range: -6.2607
Max Act: 5.7920. Min Act: -0.1700
Data Index: 5535592 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #19