Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.9888. Min Act: -0.1700
Data Index: 3017573 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.9888. Min Act: -0.1700
Data Index: 2899009 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.9575. Min Act: -0.1700
Data Index: 5140642 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.9419. Min Act: -0.1700
Data Index: 6858852 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.9419. Min Act: -0.1700
Data Index: 294292 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.9419. Min Act: -0.1700
Data Index: 1488553 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8950. Min Act: -0.1700
Data Index: 4308577 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8637. Min Act: -0.1700
Data Index: 1030295 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8637. Min Act: -0.1700
Data Index: 5322176 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8793. Min Act: -0.1700
Data Index: 4008856 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8793. Min Act: -0.1700
Data Index: 6823649 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8637. Min Act: -0.1700
Data Index: 2529338 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8637. Min Act: -0.1700
Data Index: 6148707 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8481. Min Act: -0.1700
Data Index: 4597755 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8637. Min Act: -0.1700
Data Index: 5937941 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8324. Min Act: -0.1700
Data Index: 5308532 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8324. Min Act: -0.1700
Data Index: 6268073 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8481. Min Act: -0.1700
Data Index: 5366271 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8324. Min Act: -0.1700
Data Index: 1511090 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9888. Min Range: -3.9888
Max Act: 3.8168. Min Act: -0.1700
Data Index: 6141153 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19