Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2682 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1637. Min Range: -5.1637
Max Act: 5.1637. Min Act: -0.1700
Data Index: 5154926 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.9450. Min Act: -0.1700
Data Index: 4523565 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.8825. Min Act: -0.1700
Data Index: 428778 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7887. Min Act: -0.1700
Data Index: 5837492 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7575. Min Act: -0.1700
Data Index: 8505855 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7575. Min Act: -0.1700
Data Index: 2590592 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7575. Min Act: -0.1700
Data Index: 1362446 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7262. Min Act: -0.1700
Data Index: 1362447 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7262. Min Act: -0.1700
Data Index: 5811306 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.7262. Min Act: -0.1700
Data Index: 7673738 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6949. Min Act: -0.1700
Data Index: 8163554 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6637. Min Act: -0.1700
Data Index: 2939131 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6324. Min Act: -0.1700
Data Index: 1347401 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6012. Min Act: -0.1700
Data Index: 4915596 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6324. Min Act: -0.1700
Data Index: 5301625 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6012. Min Act: -0.1700
Data Index: 7936778 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6012. Min Act: -0.1700
Data Index: 2512818 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6012. Min Act: -0.1700
Data Index: 3816076 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6012. Min Act: -0.1700
Data Index: 351356 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1637. Min Range: -5.1637
Max Act: 4.6012. Min Act: -0.1700
Data Index: 2148622 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #19