Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5805 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.8850. Min Act: -0.1700
Data Index: 5162509 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.7600. Min Act: -0.1700
Data Index: 8440777 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.4475. Min Act: -0.1700
Data Index: 7181298 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.4475. Min Act: -0.1700
Data Index: 7969870 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.3850. Min Act: -0.1700
Data Index: 445341 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.3850. Min Act: -0.1700
Data Index: 976456 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.1975. Min Act: -0.1700
Data Index: 5207 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.0725. Min Act: -0.1700
Data Index: 7910127 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.0725. Min Act: -0.1700
Data Index: 2064478 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.8850. Min Range: -12.8850
Max Act: 12.0100. Min Act: -0.1700
Data Index: 2692842 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.9475. Min Act: -0.1700
Data Index: 1578634 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.9475. Min Act: -0.1700
Data Index: 5926678 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.9475. Min Act: -0.1700
Data Index: 4587159 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.8850. Min Act: -0.1700
Data Index: 1619143 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.8850. Min Act: -0.1700
Data Index: 705135 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.8850. Min Act: -0.1700
Data Index: 3753026 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.8225. Min Act: -0.1700
Data Index: 5087760 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.8225. Min Act: -0.1700
Data Index: 75361 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.7600. Min Act: -0.1700
Data Index: 7382027 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.8850. Min Range: -12.8850
Max Act: 11.7600. Min Act: -0.1700
Data Index: 186996 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19