Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1824 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.6418. Min Act: -0.1700
Data Index: 8302646 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.5949. Min Act: -0.1700
Data Index: 6089696 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.5166. Min Act: -0.1700
Data Index: 4151769 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.5166. Min Act: -0.1700
Data Index: 2628478 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4853. Min Act: -0.1700
Data Index: 2795821 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4696. Min Act: -0.1700
Data Index: 873856 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4696. Min Act: -0.1700
Data Index: 4151770 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4383. Min Act: -0.1700
Data Index: 2297211 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4226. Min Act: -0.1700
Data Index: 2021374 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3912. Min Act: -0.1700
Data Index: 5147374 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4069. Min Act: -0.1700
Data Index: 6051083 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4069. Min Act: -0.1700
Data Index: 8227918 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3756. Min Act: -0.1700
Data Index: 8367514 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.4069. Min Act: -0.1700
Data Index: 7397909 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3756. Min Act: -0.1700
Data Index: 2818336 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3442. Min Act: -0.1700
Data Index: 3930177 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3756. Min Act: -0.1700
Data Index: 5279837 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3442. Min Act: -0.1700
Data Index: 7899624 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3285. Min Act: -0.1700
Data Index: 2627935 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6418. Min Range: -3.6418
Max Act: 3.3285. Min Act: -0.1700
Data Index: 3962242 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19