Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3849 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.4639. Min Act: -0.1700
Data Index: 2471529 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.4639. Min Act: -0.1700
Data Index: 8302359 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.4639. Min Act: -0.1700
Data Index: 5066993 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.4014. Min Act: -0.1700
Data Index: 1903298 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.3702. Min Act: -0.1700
Data Index: 7027131 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.3389. Min Act: -0.1700
Data Index: 8549006 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.2452. Min Act: -0.1700
Data Index: 6618096 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.2139. Min Act: -0.1700
Data Index: 5546477 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.2139. Min Act: -0.1700
Data Index: 1509562 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.2139. Min Act: -0.1700
Data Index: 4303500 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.2139. Min Act: -0.1700
Data Index: 1643092 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.2139. Min Act: -0.1700
Data Index: 7036029 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1827. Min Act: -0.1700
Data Index: 4050928 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1827. Min Act: -0.1700
Data Index: 5056423 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1514. Min Act: -0.1700
Data Index: 416453 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1514. Min Act: -0.1700
Data Index: 4883062 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1827. Min Act: -0.1700
Data Index: 4583247 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1514. Min Act: -0.1700
Data Index: 6784846 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1514. Min Act: -0.1700
Data Index: 5581638 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4639. Min Range: -4.4639
Max Act: 4.1514. Min Act: -0.1700
Data Index: 4199044 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19