Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1667 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.6792. Min Act: -0.1700
Data Index: 1608549 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7417. Min Range: -6.7417
Max Act: 5.7417. Min Act: -0.1700
Data Index: 2335538 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.7417. Min Act: -0.1700
Data Index: 1608541 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.7104. Min Act: -0.1700
Data Index: 1608556 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.6479. Min Act: -0.1700
Data Index: 8582595 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.6792. Min Act: -0.1700
Data Index: 4478069 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.5542. Min Act: -0.1700
Data Index: 2745802 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.2104. Min Act: -0.1700
Data Index: 1608555 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.1792. Min Act: -0.1700
Data Index: 185676 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.1167. Min Act: -0.1700
Data Index: 5736283 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.1479. Min Act: -0.1700
Data Index: 5736288 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.0229. Min Act: -0.1700
Data Index: 1608544 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.0229. Min Act: -0.1700
Data Index: 1608546 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7417. Min Range: -6.7417
Max Act: 5.9917. Min Act: -0.1700
Data Index: 4439977 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7417. Min Range: -6.7417
Max Act: 5.8354. Min Act: -0.1700
Data Index: 6876168 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7417. Min Range: -6.7417
Max Act: 5.9917. Min Act: -0.1700
Data Index: 3972276 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7417. Min Range: -6.7417
Max Act: 6.0229. Min Act: -0.1700
Data Index: 3066497 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7417. Min Range: -6.7417
Max Act: 5.9292. Min Act: -0.1700
Data Index: 4313121 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7417. Min Range: -6.7417
Max Act: 5.9604. Min Act: -0.1700
Data Index: 4076417 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7417. Min Range: -6.7417
Max Act: 5.9917. Min Act: -0.1700
Data Index: 8625887 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #19