Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 285 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1956. Min Range: -6.1956
Max Act: 6.1956. Min Act: -0.1700
Data Index: 2375167 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.9456. Min Act: -0.1700
Data Index: 4247884 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.8831. Min Act: -0.1700
Data Index: 723635 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.7581. Min Act: -0.1700
Data Index: 5043308 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.7268. Min Act: -0.1700
Data Index: 3529568 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.6956. Min Act: -0.1700
Data Index: 712684 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.6956. Min Act: -0.1700
Data Index: 783489 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.6331. Min Act: -0.1700
Data Index: 3067800 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.6018. Min Act: -0.1700
Data Index: 3488586 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.6331. Min Act: -0.1700
Data Index: 163623 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.6018. Min Act: -0.1700
Data Index: 425559 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.6018. Min Act: -0.1700
Data Index: 1945119 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5706. Min Act: -0.1700
Data Index: 1832309 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5706. Min Act: -0.1700
Data Index: 8501531 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5706. Min Act: -0.1700
Data Index: 7095894 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5706. Min Act: -0.1700
Data Index: 5495896 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5393. Min Act: -0.1700
Data Index: 3686491 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5081. Min Act: -0.1700
Data Index: 5046507 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5081. Min Act: -0.1700
Data Index: 3345392 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1956. Min Range: -6.1956
Max Act: 5.5393. Min Act: -0.1700
Data Index: 1103965 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #19