Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4094 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.3387. Min Act: -0.1700
Data Index: 2243172 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.3075. Min Act: -0.1700
Data Index: 5485631 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.2137. Min Act: -0.1700
Data Index: 6607371 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.1825. Min Act: -0.1700
Data Index: 1713141 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.1512. Min Act: -0.1700
Data Index: 1650356 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.0887. Min Act: -0.1700
Data Index: 7219860 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.0887. Min Act: -0.1700
Data Index: 3497614 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3387. Min Range: -5.3387
Max Act: 5.0262. Min Act: -0.1700
Data Index: 3009337 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9637. Min Act: -0.1700
Data Index: 5642367 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9637. Min Act: -0.1700
Data Index: 8386959 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9637. Min Act: -0.1700
Data Index: 8072083 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9325. Min Act: -0.1700
Data Index: 5061177 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9637. Min Act: -0.1700
Data Index: 5234639 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9637. Min Act: -0.1700
Data Index: 8499568 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9012. Min Act: -0.1700
Data Index: 2202847 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9012. Min Act: -0.1700
Data Index: 1913658 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.8700. Min Act: -0.1700
Data Index: 5918150 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9012. Min Act: -0.1700
Data Index: 3012753 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.9325. Min Act: -0.1700
Data Index: 728787 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3387. Min Range: -5.3387
Max Act: 4.8700. Min Act: -0.1700
Data Index: 4023102 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19