Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5188 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.1390. Min Act: -0.1700
Data Index: 4110782 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.2015. Min Act: -0.1700
Data Index: 4665166 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.2015. Min Act: -0.1700
Data Index: 2765218 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.0140. Min Act: -0.1700
Data Index: 2478998 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.0765. Min Act: -0.1700
Data Index: 2190198 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 502655 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.0140. Min Act: -0.1700
Data Index: 3626777 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 5611271 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.0140. Min Act: -0.1700
Data Index: 5444023 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 5176820 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 4601045 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 4489991 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 5175728 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 3612638 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 5980808 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 3101535 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.2015. Min Range: -12.2015
Max Act: 12.0140. Min Act: -0.1700
Data Index: 6625209 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 4111995 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 6789371 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.2015. Min Range: -12.2015
Max Act: 11.9515. Min Act: -0.1700
Data Index: 7505295 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19