Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4867 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.8557. Min Act: -0.1700
Data Index: 6265124 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.7932. Min Act: -0.1700
Data Index: 1309711 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.7307. Min Act: -0.1700
Data Index: 4139699 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.6682. Min Act: -0.1700
Data Index: 1309714 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.6682. Min Act: -0.1700
Data Index: 1309712 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.6369. Min Act: -0.1700
Data Index: 2388714 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.6057. Min Act: -0.1700
Data Index: 5839042 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.5432. Min Act: -0.1700
Data Index: 3203150 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4807. Min Act: -0.1700
Data Index: 8435159 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.5119. Min Act: -0.1700
Data Index: 4634255 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4494. Min Act: -0.1700
Data Index: 832822 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 6376193 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 8274360 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 6056949 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.4182. Min Act: -0.1700
Data Index: 4139700 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3869. Min Act: -0.1700
Data Index: 6411257 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3869. Min Act: -0.1700
Data Index: 601473 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3869. Min Act: -0.1700
Data Index: 3920167 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3869. Min Act: -0.1700
Data Index: 5564884 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8557. Min Range: -5.8557
Max Act: 5.3869. Min Act: -0.1700
Data Index: 832821 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #19