Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.8455. Min Act: -0.1700
Data Index: 1045722 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.8767. Min Act: -0.1700
Data Index: 8400355 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.7830. Min Act: -0.1700
Data Index: 8425164 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.7517. Min Act: -0.1700
Data Index: 4384690 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.6580. Min Act: -0.1700
Data Index: 5793218 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.6267. Min Act: -0.1700
Data Index: 2731456 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.6267. Min Act: -0.1700
Data Index: 2824148 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5955. Min Act: -0.1700
Data Index: 8745760 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5642. Min Act: -0.1700
Data Index: 7933553 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5642. Min Act: -0.1700
Data Index: 6757966 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5642. Min Act: -0.1700
Data Index: 1173820 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5642. Min Act: -0.1700
Data Index: 1045723 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5642. Min Act: -0.1700
Data Index: 3597366 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5642. Min Act: -0.1700
Data Index: 4734603 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5642. Min Act: -0.1700
Data Index: 7438223 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5330. Min Act: -0.1693
Data Index: 8067369 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5017. Min Act: -0.1700
Data Index: 5619415 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5330. Min Act: -0.1700
Data Index: 6829440 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.5017. Min Act: -0.1700
Data Index: 7090669 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8767. Min Range: -5.8767
Max Act: 5.4705. Min Act: -0.1700
Data Index: 4635925 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19