Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4029 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.8159. Min Act: -0.1700
Data Index: 5230497 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.7847. Min Act: -0.1700
Data Index: 2326306 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.7222. Min Act: -0.1700
Data Index: 6543957 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.7222. Min Act: -0.1700
Data Index: 4019711 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.6909. Min Act: -0.1700
Data Index: 2213795 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.6597. Min Act: -0.1700
Data Index: 4952038 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.6597. Min Act: -0.1700
Data Index: 7869262 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5659. Min Act: -0.1700
Data Index: 3207586 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5972. Min Act: -0.1700
Data Index: 344477 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5659. Min Act: -0.1700
Data Index: 4019710 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5659. Min Act: -0.1700
Data Index: 7461675 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5347. Min Act: -0.1700
Data Index: 966502 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5347. Min Act: -0.1700
Data Index: 1987486 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5347. Min Act: -0.1700
Data Index: 7155603 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.4722. Min Act: -0.1700
Data Index: 5287594 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.5034. Min Act: -0.1700
Data Index: 4243140 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.4722. Min Act: -0.1700
Data Index: 4695609 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.4409. Min Act: -0.1700
Data Index: 2654572 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.4097. Min Act: -0.1700
Data Index: 366366 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8159. Min Range: -5.8159
Max Act: 5.3784. Min Act: -0.1700
Data Index: 140968 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19