Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 992 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1607. Min Range: -4.1607
Max Act: 4.1607. Min Act: -0.1700
Data Index: 8810494 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1607. Min Range: -4.1607
Max Act: 4.0982. Min Act: -0.1700
Data Index: 7764016 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1607. Min Range: -4.1607
Max Act: 4.0825. Min Act: -0.1700
Data Index: 4212666 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1607. Min Range: -4.1607
Max Act: 4.0200. Min Act: -0.1700
Data Index: 5183639 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1607. Min Range: -4.1607
Max Act: 4.0200. Min Act: -0.1700
Data Index: 689510 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1607. Min Range: -4.1607
Max Act: 4.0200. Min Act: -0.1700
Data Index: 6793999 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.9887. Min Act: -0.1700
Data Index: 3544805 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8950. Min Act: -0.1700
Data Index: 8110833 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8950. Min Act: -0.1700
Data Index: 7827690 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8950. Min Act: -0.1700
Data Index: 219631 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8950. Min Act: -0.1700
Data Index: 726834 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8793. Min Act: -0.1700
Data Index: 2408729 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8793. Min Act: -0.1700
Data Index: 4015297 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8637. Min Act: -0.1700
Data Index: 242066 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8793. Min Act: -0.1700
Data Index: 5548611 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8481. Min Act: -0.1700
Data Index: 7557597 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8481. Min Act: -0.1700
Data Index: 4998792 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8324. Min Act: -0.1700
Data Index: 4778964 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8168. Min Act: -0.1700
Data Index: 3701223 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1607. Min Range: -4.1607
Max Act: 3.8324. Min Act: -0.1700
Data Index: 3717913 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #19