Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1726 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.4375. Min Act: -0.1700
Data Index: 8479255 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.4063. Min Act: -0.1700
Data Index: 1103557 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.3750. Min Act: -0.1700
Data Index: 1440649 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.3438. Min Act: -0.1700
Data Index: 6202639 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.3125. Min Act: -0.1700
Data Index: 7634613 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.3125. Min Act: -0.1700
Data Index: 3003583 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2813. Min Act: -0.1700
Data Index: 1592924 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2188. Min Act: -0.1700
Data Index: 1229201 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2500. Min Act: -0.1700
Data Index: 2962413 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2188. Min Act: -0.1700
Data Index: 8384980 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1875. Min Act: -0.1700
Data Index: 7321789 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1875. Min Act: -0.1700
Data Index: 1013896 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.2188. Min Act: -0.1700
Data Index: 5279106 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1563. Min Act: -0.1700
Data Index: 4236025 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1563. Min Act: -0.1700
Data Index: 6182363 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1563. Min Act: -0.1700
Data Index: 8657227 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1250. Min Act: -0.1700
Data Index: 5107128 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1250. Min Act: -0.1700
Data Index: 3397425 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.0938. Min Act: -0.1700
Data Index: 7213303 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4375. Min Range: -6.4375
Max Act: 6.1250. Min Act: -0.1700
Data Index: 1440638 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19