Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3102 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.6848. Min Act: -0.1700
Data Index: 5914478 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.6223. Min Act: -0.1700
Data Index: 370330 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.4973. Min Act: -0.1700
Data Index: 7641495 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.4348. Min Act: -0.1700
Data Index: 1987318 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.3723. Min Act: -0.1700
Data Index: 456843 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.3098. Min Act: -0.1700
Data Index: 298818 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.3411. Min Act: -0.1700
Data Index: 6215430 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.3098. Min Act: -0.1700
Data Index: 6570093 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.3098. Min Act: -0.1700
Data Index: 512844 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.2786. Min Act: -0.1700
Data Index: 2572529 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.2473. Min Act: -0.1700
Data Index: 2312968 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.2473. Min Act: -0.1700
Data Index: 2253035 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.1536. Min Act: -0.1700
Data Index: 4547429 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.1223. Min Act: -0.1700
Data Index: 8004278 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.1536. Min Act: -0.1700
Data Index: 6221763 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.1223. Min Act: -0.1700
Data Index: 8605452 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.1223. Min Act: -0.1700
Data Index: 704634 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.1223. Min Act: -0.1700
Data Index: 8657988 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.1223. Min Act: -0.1700
Data Index: 8637843 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6848. Min Range: -6.6848
Max Act: 6.0911. Min Act: -0.1700
Data Index: 989445 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #19