Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1871 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.4773. Min Act: -0.1700
Data Index: 6503803 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.4461. Min Act: -0.1700
Data Index: 8226391 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.2586. Min Act: -0.1700
Data Index: 6985383 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.1648. Min Act: -0.1700
Data Index: 7869606 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.1023. Min Act: -0.1700
Data Index: 3015496 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.1023. Min Act: -0.1700
Data Index: 5974942 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.1023. Min Act: -0.1700
Data Index: 6926435 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.0398. Min Act: -0.1700
Data Index: 7572936 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.0086. Min Act: -0.1700
Data Index: 2069919 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.0711. Min Act: -0.1700
Data Index: 2308523 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.0086. Min Act: -0.1700
Data Index: 604347 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4773. Min Range: -7.4773
Max Act: 7.0086. Min Act: -0.1700
Data Index: 31273 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9773. Min Act: -0.1700
Data Index: 3632937 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9773. Min Act: -0.1700
Data Index: 926815 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9773. Min Act: -0.1700
Data Index: 4672367 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9148. Min Act: -0.1700
Data Index: 4381983 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9148. Min Act: -0.1700
Data Index: 6731691 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9148. Min Act: -0.1700
Data Index: 5710293 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9148. Min Act: -0.1700
Data Index: 868610 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4773. Min Range: -7.4773
Max Act: 6.9148. Min Act: -0.1700
Data Index: 4542389 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #19