Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3960 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.2811. Min Act: -0.1700
Data Index: 8762903 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.2498. Min Act: -0.1700
Data Index: 5449420 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.2186. Min Act: -0.1700
Data Index: 1485271 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.2186. Min Act: -0.1700
Data Index: 5394152 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.1873. Min Act: -0.1700
Data Index: 5960415 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.0623. Min Act: -0.1700
Data Index: 8415935 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2811. Min Range: -6.2811
Max Act: 6.0311. Min Act: -0.1700
Data Index: 1417240 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9686. Min Act: -0.1700
Data Index: 24825 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9686. Min Act: -0.1700
Data Index: 7930829 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9373. Min Act: -0.1700
Data Index: 6322934 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9061. Min Act: -0.1700
Data Index: 1721670 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9061. Min Act: -0.1700
Data Index: 323521 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9061. Min Act: -0.1700
Data Index: 7081911 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9373. Min Act: -0.1700
Data Index: 4392106 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8748. Min Act: -0.1700
Data Index: 3819006 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.9061. Min Act: -0.1700
Data Index: 39768 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8748. Min Act: -0.1700
Data Index: 3540119 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8436. Min Act: -0.1700
Data Index: 4022423 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8436. Min Act: -0.1700
Data Index: 3662791 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2811. Min Range: -6.2811
Max Act: 5.8436. Min Act: -0.1700
Data Index: 380867 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #19