Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3840 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.5151. Min Act: -0.1700
Data Index: 3774911 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.4213. Min Act: -0.1700
Data Index: 5669281 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.3276. Min Act: -0.1700
Data Index: 7218609 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.3588. Min Act: -0.1700
Data Index: 8665438 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.3276. Min Act: -0.1700
Data Index: 1623470 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.1713. Min Act: -0.1700
Data Index: 141032 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.1713. Min Act: -0.1700
Data Index: 3335665 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.1088. Min Act: -0.1700
Data Index: 7119966 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.0776. Min Act: -0.1700
Data Index: 771674 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.0776. Min Act: -0.1700
Data Index: 7508722 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.0151. Min Act: -0.1700
Data Index: 8549146 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.0151. Min Act: -0.1700
Data Index: 1271221 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.0151. Min Act: -0.1700
Data Index: 5334054 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5151. Min Range: -6.5151
Max Act: 6.0151. Min Act: -0.1700
Data Index: 6368664 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5151. Min Range: -6.5151
Max Act: 5.9838. Min Act: -0.1700
Data Index: 1541102 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5151. Min Range: -6.5151
Max Act: 5.9526. Min Act: -0.1700
Data Index: 6782991 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5151. Min Range: -6.5151
Max Act: 5.9526. Min Act: -0.1700
Data Index: 989486 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5151. Min Range: -6.5151
Max Act: 5.9526. Min Act: -0.1700
Data Index: 1683294 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5151. Min Range: -6.5151
Max Act: 5.9213. Min Act: -0.1700
Data Index: 3085925 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5151. Min Range: -6.5151
Max Act: 5.8901. Min Act: -0.1700
Data Index: 33397 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19