Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3928 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.6057. Min Act: -0.1700
Data Index: 524932 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.5432. Min Act: -0.1700
Data Index: 3366222 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.5432. Min Act: -0.1700
Data Index: 4106109 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.5744. Min Act: -0.1700
Data Index: 6357458 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.5432. Min Act: -0.1700
Data Index: 5878637 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.4807. Min Act: -0.1700
Data Index: 8714508 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.4182. Min Act: -0.1700
Data Index: 8738302 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3869. Min Act: -0.1700
Data Index: 4913790 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3869. Min Act: -0.1700
Data Index: 8647781 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3869. Min Act: -0.1700
Data Index: 8005456 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3869. Min Act: -0.1700
Data Index: 4702629 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3557. Min Act: -0.1700
Data Index: 1006519 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3244. Min Act: -0.1700
Data Index: 3786949 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3557. Min Act: -0.1700
Data Index: 8322018 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3557. Min Act: -0.1700
Data Index: 2194155 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3244. Min Act: -0.1700
Data Index: 7514792 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.3244. Min Act: -0.1700
Data Index: 7093705 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.2931. Min Act: -0.1700
Data Index: 5608549 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.2931. Min Act: -0.1700
Data Index: 1893608 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6057. Min Range: -4.6057
Max Act: 4.2931. Min Act: -0.1700
Data Index: 2102459 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #19