Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5723 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.9324. Min Act: -0.1700
Data Index: 8426846 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.9324. Min Act: -0.1700
Data Index: 3438916 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.9154. Min Act: -0.1700
Data Index: 4488668 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.9154. Min Act: -0.1700
Data Index: 1846771 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.9154. Min Act: -0.1700
Data Index: 721424 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.9154. Min Act: -0.1700
Data Index: 2206609 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.9154. Min Act: -0.1700
Data Index: 7870196 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8983. Min Act: -0.1700
Data Index: 6767245 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8983. Min Act: -0.1700
Data Index: 7709049 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8983. Min Act: -0.1700
Data Index: 3774240 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8812. Min Act: -0.1700
Data Index: 8701936 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8812. Min Act: -0.1700
Data Index: 6519351 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8812. Min Act: -0.1700
Data Index: 4513588 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8812. Min Act: -0.1700
Data Index: 1328656 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8641. Min Act: -0.1700
Data Index: 8426849 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8641. Min Act: -0.1700
Data Index: 3746807 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8641. Min Act: -0.1700
Data Index: 3540825 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8641. Min Act: -0.1700
Data Index: 4319270 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8641. Min Act: -0.1700
Data Index: 164402 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9324. Min Range: -1.9324
Max Act: 1.8641. Min Act: -0.1700
Data Index: 3108951 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19