Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3348 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3290. Min Range: -8.3290
Max Act: 8.3290. Min Act: -0.1700
Data Index: 2438832 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3290. Min Range: -8.3290
Max Act: 8.0790. Min Act: -0.1700
Data Index: 5776667 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3290. Min Range: -8.3290
Max Act: 8.0790. Min Act: -0.1700
Data Index: 764199 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3290. Min Range: -8.3290
Max Act: 8.0165. Min Act: -0.1700
Data Index: 5808360 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3290. Min Range: -8.3290
Max Act: 8.0165. Min Act: -0.1700
Data Index: 2182352 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3290. Min Range: -8.3290
Max Act: 8.0165. Min Act: -0.1700
Data Index: 4050 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 1348101 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 6450150 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.8915. Min Act: -0.1700
Data Index: 2986278 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 6662357 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 1196270 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 8366285 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 8158583 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 821394 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.9540. Min Act: -0.1700
Data Index: 7925085 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.8915. Min Act: -0.1700
Data Index: 2796127 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.8915. Min Act: -0.1700
Data Index: 2816951 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.8915. Min Act: -0.1700
Data Index: 1701290 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.8915. Min Act: -0.1700
Data Index: 352263 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3290. Min Range: -8.3290
Max Act: 7.8290. Min Act: -0.1700
Data Index: 257459 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19