Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1753 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.7611. Min Act: -0.1700
Data Index: 2074815 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.7298. Min Act: -0.1700
Data Index: 646236 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6673. Min Act: -0.1700
Data Index: 7494920 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6360. Min Act: -0.1700
Data Index: 3756487 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6360. Min Act: -0.1700
Data Index: 1051933 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6360. Min Act: -0.1700
Data Index: 6579173 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6047. Min Act: -0.1700
Data Index: 5343477 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6047. Min Act: -0.1700
Data Index: 1136638 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6047. Min Act: -0.1700
Data Index: 1867281 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6047. Min Act: -0.1700
Data Index: 2456320 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6047. Min Act: -0.1700
Data Index: 4176754 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.6047. Min Act: -0.1700
Data Index: 6951659 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5420. Min Act: -0.1700
Data Index: 2356094 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5734. Min Act: -0.1700
Data Index: 5888641 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5734. Min Act: -0.1700
Data Index: 6653800 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5420. Min Act: -0.1700
Data Index: 6131995 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5420. Min Act: -0.1700
Data Index: 1919750 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5420. Min Act: -0.1700
Data Index: 174011 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5420. Min Act: -0.1700
Data Index: 3497040 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7611. Min Range: -3.7611
Max Act: 3.5420. Min Act: -0.1700
Data Index: 1956284 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19