Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3911 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.7440. Min Act: -0.1700
Data Index: 3600902 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.7128. Min Act: -0.1700
Data Index: 3215499 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.6815. Min Act: -0.1700
Data Index: 214805 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.5878. Min Act: -0.1700
Data Index: 1686985 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.5565. Min Act: -0.1700
Data Index: 8402825 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.5253. Min Act: -0.1700
Data Index: 7593796 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.5565. Min Act: -0.1700
Data Index: 2802722 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.5565. Min Act: -0.1700
Data Index: 4141396 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.5565. Min Act: -0.1700
Data Index: 490543 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.5253. Min Act: -0.1700
Data Index: 4580881 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4940. Min Act: -0.1700
Data Index: 7880494 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4628. Min Act: -0.1700
Data Index: 4508588 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4315. Min Act: -0.1700
Data Index: 4184735 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4315. Min Act: -0.1700
Data Index: 5683251 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4315. Min Act: -0.1700
Data Index: 7984006 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4003. Min Act: -0.1700
Data Index: 5332318 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4003. Min Act: -0.1700
Data Index: 7917720 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4315. Min Act: -0.1700
Data Index: 595934 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4003. Min Act: -0.1700
Data Index: 7858892 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7440. Min Range: -7.7440
Max Act: 7.4315. Min Act: -0.1700
Data Index: 1244593 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19