Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2062 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5429. Min Range: -5.5429
Max Act: 5.5429. Min Act: -0.1700
Data Index: 3581404 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5429. Min Range: -5.5429
Max Act: 5.3241. Min Act: -0.1700
Data Index: 550161 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5429. Min Range: -5.5429
Max Act: 5.1991. Min Act: -0.1700
Data Index: 6651107 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5429. Min Range: -5.5429
Max Act: 5.1054. Min Act: -0.1700
Data Index: 7760403 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.9804. Min Act: -0.1700
Data Index: 5058267 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.9491. Min Act: -0.1700
Data Index: 4620398 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.8554. Min Act: -0.1700
Data Index: 6130854 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.8866. Min Act: -0.1700
Data Index: 5149907 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.8241. Min Act: -0.1700
Data Index: 4184079 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.8241. Min Act: -0.1700
Data Index: 3491219 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7929. Min Act: -0.1700
Data Index: 811781 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7929. Min Act: -0.1700
Data Index: 280502 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7616. Min Act: -0.1700
Data Index: 638794 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7304. Min Act: -0.1700
Data Index: 964687 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7304. Min Act: -0.1700
Data Index: 1210122 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7304. Min Act: -0.1700
Data Index: 912835 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7304. Min Act: -0.1700
Data Index: 8496874 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.7616. Min Act: -0.1700
Data Index: 1584431 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.6991. Min Act: -0.1700
Data Index: 6989025 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5429. Min Range: -5.5429
Max Act: 4.6679. Min Act: -0.1700
Data Index: 3311397 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19