Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4842 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.5701. Min Act: -0.1700
Data Index: 3666943 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.5701. Min Act: -0.1700
Data Index: 6455078 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.5076. Min Act: -0.1700
Data Index: 8689826 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.3826. Min Act: -0.1700
Data Index: 7237380 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.3201. Min Act: -0.1700
Data Index: 5127051 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.3201. Min Act: -0.1700
Data Index: 6352877 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.2576. Min Act: -0.1700
Data Index: 3457100 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.2576. Min Act: -0.1700
Data Index: 1506615 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1951. Min Act: -0.1700
Data Index: 1116675 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1951. Min Act: -0.1700
Data Index: 7719132 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 3372113 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 1153442 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 288156 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 5141189 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 5283702 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 5286978 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 5941156 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 1902382 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 3816473 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5701. Min Range: -8.5701
Max Act: 8.1326. Min Act: -0.1700
Data Index: 649423 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19