Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4827 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1560. Min Range: -3.1560
Max Act: 3.1560. Min Act: -0.1700
Data Index: 3593771 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1560. Min Range: -3.1560
Max Act: 3.0930. Min Act: -0.1700
Data Index: 6105079 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1560. Min Range: -3.1560
Max Act: 3.0615. Min Act: -0.1700
Data Index: 3930197 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1560. Min Range: -3.1560
Max Act: 3.0299. Min Act: -0.1700
Data Index: 7599330 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9983. Min Act: -0.1700
Data Index: 6932335 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1560. Min Range: -3.1560
Max Act: 3.0141. Min Act: -0.1700
Data Index: 2392010 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1560. Min Range: -3.1560
Max Act: 3.0141. Min Act: -0.1700
Data Index: 709299 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9825. Min Act: -0.1700
Data Index: 927081 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9983. Min Act: -0.1700
Data Index: 8005512 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9825. Min Act: -0.1700
Data Index: 6955938 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9825. Min Act: -0.1700
Data Index: 8449944 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9667. Min Act: -0.1700
Data Index: 1810484 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9825. Min Act: -0.1700
Data Index: 982853 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9508. Min Act: -0.1700
Data Index: 427031 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9192. Min Act: -0.1700
Data Index: 7463581 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9508. Min Act: -0.1700
Data Index: 988519 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9192. Min Act: -0.1700
Data Index: 2673791 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9192. Min Act: -0.1700
Data Index: 1781349 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9192. Min Act: -0.1700
Data Index: 3516063 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1560. Min Range: -3.1560
Max Act: 2.9033. Min Act: -0.1700
Data Index: 4493547 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19