Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2884 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.2620. Min Range: -10.2620
Max Act: 10.2620. Min Act: -0.1700
Data Index: 7579619 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.2620. Min Range: -10.2620
Max Act: 10.1995. Min Act: -0.1700
Data Index: 4916237 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.2620. Min Range: -10.2620
Max Act: 10.0745. Min Act: -0.1700
Data Index: 1810983 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.8870. Min Act: -0.1700
Data Index: 2558477 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.8245. Min Act: -0.1700
Data Index: 6140221 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.8245. Min Act: -0.1700
Data Index: 1991991 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.7620. Min Act: -0.1700
Data Index: 4687313 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.8245. Min Act: -0.1700
Data Index: 6430029 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.7620. Min Act: -0.1700
Data Index: 6344880 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.6995. Min Act: -0.1700
Data Index: 7755004 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.6995. Min Act: -0.1700
Data Index: 6716325 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.6370. Min Act: -0.1700
Data Index: 8635022 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.6370. Min Act: -0.1700
Data Index: 6612363 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.6370. Min Act: -0.1700
Data Index: 1885368 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.6370. Min Act: -0.1700
Data Index: 5614472 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.6370. Min Act: -0.1700
Data Index: 6007604 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.5745. Min Act: -0.1700
Data Index: 1553179 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.5120. Min Act: -0.1700
Data Index: 1026230 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.5745. Min Act: -0.1700
Data Index: 6872687 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.2620. Min Range: -10.2620
Max Act: 9.5745. Min Act: -0.1700
Data Index: 2428727 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #19