Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3209 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.9554. Min Act: -0.1700
Data Index: 625585 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.9867. Min Act: -0.1700
Data Index: 8649660 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.9242. Min Act: -0.1700
Data Index: 5367976 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.9242. Min Act: -0.1700
Data Index: 6222507 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.9242. Min Act: -0.1700
Data Index: 1075554 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.8929. Min Act: -0.1700
Data Index: 1622850 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.8929. Min Act: -0.1700
Data Index: 8659553 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7992. Min Act: -0.1700
Data Index: 7272387 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7679. Min Act: -0.1700
Data Index: 1390288 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7679. Min Act: -0.1700
Data Index: 6836100 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7679. Min Act: -0.1700
Data Index: 1823628 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7054. Min Act: -0.1700
Data Index: 1488541 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7367. Min Act: -0.1700
Data Index: 6544199 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7367. Min Act: -0.1700
Data Index: 3313511 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7367. Min Act: -0.1700
Data Index: 8649662 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7367. Min Act: -0.1700
Data Index: 7791373 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7367. Min Act: -0.1700
Data Index: 534005 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7367. Min Act: -0.1700
Data Index: 7125521 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7054. Min Act: -0.1700
Data Index: 6950088 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9867. Min Range: -6.9867
Max Act: 6.7054. Min Act: -0.1700
Data Index: 4108548 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #19