Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1038 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.6356. Min Act: -0.1700
Data Index: 2188061 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.4794. Min Act: -0.1700
Data Index: 7026704 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.4169. Min Act: -0.1700
Data Index: 342105 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.3856. Min Act: -0.1700
Data Index: 342116 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2919. Min Act: -0.1700
Data Index: 1594772 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2919. Min Act: -0.1700
Data Index: 5334321 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2606. Min Act: -0.1700
Data Index: 471523 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2294. Min Act: -0.1700
Data Index: 1801609 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.2294. Min Act: -0.1700
Data Index: 6121368 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1981. Min Act: -0.1700
Data Index: 5250923 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1981. Min Act: -0.1700
Data Index: 8775594 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1669. Min Act: -0.1700
Data Index: 5181627 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1669. Min Act: -0.1700
Data Index: 3623125 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1669. Min Act: -0.1700
Data Index: 6526678 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1669. Min Act: -0.1700
Data Index: 1922475 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1356. Min Act: -0.1700
Data Index: 818795 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1356. Min Act: -0.1700
Data Index: 6372694 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1356. Min Act: -0.1700
Data Index: 7329770 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1356. Min Act: -0.1700
Data Index: 7738423 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6356. Min Range: -5.6356
Max Act: 5.1044. Min Act: -0.1700
Data Index: 897085 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19