Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2535 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1526. Min Range: -5.1526
Max Act: 5.1526. Min Act: -0.1700
Data Index: 235672 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1526. Min Range: -5.1526
Max Act: 5.0589. Min Act: -0.1700
Data Index: 3462854 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1526. Min Range: -5.1526
Max Act: 5.0276. Min Act: -0.1700
Data Index: 2231811 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1526. Min Range: -5.1526
Max Act: 5.0276. Min Act: -0.1700
Data Index: 2156116 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.9651. Min Act: -0.1700
Data Index: 69328 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.9339. Min Act: -0.1700
Data Index: 7440366 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.9026. Min Act: -0.1700
Data Index: 5389322 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.8714. Min Act: -0.1700
Data Index: 2489633 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.8714. Min Act: -0.1700
Data Index: 1944485 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.8714. Min Act: -0.1700
Data Index: 3708853 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.8401. Min Act: -0.1700
Data Index: 1150079 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.8089. Min Act: -0.1700
Data Index: 5761034 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.8089. Min Act: -0.1700
Data Index: 6687603 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.7464. Min Act: -0.1700
Data Index: 6805039 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.7464. Min Act: -0.1700
Data Index: 7688142 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.7464. Min Act: -0.1700
Data Index: 4546308 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.7151. Min Act: -0.1700
Data Index: 6086216 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.7151. Min Act: -0.1700
Data Index: 5072946 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.7151. Min Act: -0.1700
Data Index: 1940825 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1526. Min Range: -5.1526
Max Act: 4.6839. Min Act: -0.1700
Data Index: 6255360 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19