Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4531 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.9434. Min Act: -0.1700
Data Index: 6488997 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.9434. Min Act: -0.1700
Data Index: 3548749 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.8809. Min Act: -0.1700
Data Index: 6489000 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.8497. Min Act: -0.1700
Data Index: 4923993 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.8497. Min Act: -0.1700
Data Index: 5608421 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.7559. Min Act: -0.1700
Data Index: 522272 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.7559. Min Act: -0.1700
Data Index: 165210 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.6934. Min Act: -0.1700
Data Index: 500512 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.6309. Min Act: -0.1700
Data Index: 584435 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.6309. Min Act: -0.1700
Data Index: 6891337 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.6309. Min Act: -0.1700
Data Index: 2300757 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.6309. Min Act: -0.1700
Data Index: 909184 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5997. Min Act: -0.1700
Data Index: 5385974 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5684. Min Act: -0.1700
Data Index: 2642003 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5684. Min Act: -0.1700
Data Index: 7181412 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5372. Min Act: -0.1700
Data Index: 4431995 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5059. Min Act: -0.1700
Data Index: 2101187 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5059. Min Act: -0.1700
Data Index: 1372768 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5059. Min Act: -0.1700
Data Index: 5273768 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9434. Min Range: -5.9434
Max Act: 5.5059. Min Act: -0.1700
Data Index: 564034 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #19