Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5489 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.7515. Min Act: -0.1699
Data Index: 668786 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.7515. Min Act: -0.1694
Data Index: 3640685 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.7342. Min Act: -0.1700
Data Index: 3640686 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.7342. Min Act: -0.1699
Data Index: 2640116 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.7169. Min Act: -0.1652
Data Index: 610939 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1700
Data Index: 6722519 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1638
Data Index: 2160951 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1699
Data Index: 3892546 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1698
Data Index: 4450415 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1700
Data Index: 8197287 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1700
Data Index: 1700073 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1700
Data Index: 2595799 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1692
Data Index: 2534772 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6648. Min Act: -0.1662
Data Index: 1952189 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6474. Min Act: -0.1700
Data Index: 8140470 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6300. Min Act: -0.1699
Data Index: 3465225 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6126. Min Act: -0.1697
Data Index: 1452921 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6126. Min Act: -0.1696
Data Index: 6316322 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.6126. Min Act: -0.1700
Data Index: 3557712 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7515. Min Range: -1.7515
Max Act: 1.5776. Min Act: -0.1685
Data Index: 2002660 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #19