Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3945 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.7502. Min Act: -0.1700
Data Index: 7976828 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.7502. Min Act: -0.1700
Data Index: 4611372 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.7190. Min Act: -0.1700
Data Index: 8511383 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.7502. Min Act: -0.1700
Data Index: 8202874 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.7190. Min Act: -0.1700
Data Index: 1130319 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.7190. Min Act: -0.1700
Data Index: 3414584 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6877. Min Act: -0.1700
Data Index: 46214 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6877. Min Act: -0.1700
Data Index: 3753916 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6564. Min Act: -0.1700
Data Index: 8538539 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6564. Min Act: -0.1700
Data Index: 2106347 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6407. Min Act: -0.1700
Data Index: 254429 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6251. Min Act: -0.1700
Data Index: 7065575 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6251. Min Act: -0.1700
Data Index: 5792506 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.5938. Min Act: -0.1700
Data Index: 7129477 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6094. Min Act: -0.1700
Data Index: 3367731 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.5938. Min Act: -0.1700
Data Index: 4001716 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.5938. Min Act: -0.1700
Data Index: 3711265 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.6094. Min Act: -0.1700
Data Index: 2890726 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.5468. Min Act: -0.1700
Data Index: 6071632 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7502. Min Range: -3.7502
Max Act: 3.5468. Min Act: -0.1700
Data Index: 6663946 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19