Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3454 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2188. Min Range: -6.2188
Max Act: 6.2188. Min Act: -0.1700
Data Index: 956391 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2188. Min Range: -6.2188
Max Act: 6.0625. Min Act: -0.1700
Data Index: 2572659 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2188. Min Range: -6.2188
Max Act: 6.0000. Min Act: -0.1700
Data Index: 7576767 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.8750. Min Act: -0.1700
Data Index: 4313395 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.8750. Min Act: -0.1700
Data Index: 3719120 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.7813. Min Act: -0.1700
Data Index: 1614011 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.7813. Min Act: -0.1700
Data Index: 2497872 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.7500. Min Act: -0.1700
Data Index: 4403811 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.7188. Min Act: -0.1700
Data Index: 1486702 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.7188. Min Act: -0.1700
Data Index: 410551 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.7188. Min Act: -0.1700
Data Index: 5268117 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.6875. Min Act: -0.1700
Data Index: 1384308 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.6875. Min Act: -0.1700
Data Index: 5381117 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.6563. Min Act: -0.1700
Data Index: 7260234 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.6563. Min Act: -0.1700
Data Index: 1409143 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.6563. Min Act: -0.1700
Data Index: 4004667 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.6563. Min Act: -0.1700
Data Index: 5078380 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.6250. Min Act: -0.1700
Data Index: 3655328 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.5938. Min Act: -0.1700
Data Index: 5587374 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2188. Min Range: -6.2188
Max Act: 5.5938. Min Act: -0.1700
Data Index: 4729595 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #19