Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3334 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.9721. Min Act: -0.1700
Data Index: 133581 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.9404. Min Act: -0.1700
Data Index: 8800863 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.9246. Min Act: -0.1700
Data Index: 7593642 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8929. Min Act: -0.1700
Data Index: 7814116 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.9087. Min Act: -0.1700
Data Index: 6189551 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8770. Min Act: -0.1700
Data Index: 7136777 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8452. Min Act: -0.1700
Data Index: 6588407 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8452. Min Act: -0.1700
Data Index: 2536343 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8452. Min Act: -0.1700
Data Index: 8035557 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8452. Min Act: -0.1700
Data Index: 808715 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8452. Min Act: -0.1700
Data Index: 7194371 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8293. Min Act: -0.1700
Data Index: 3234778 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8134. Min Act: -0.1700
Data Index: 4666298 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8134. Min Act: -0.1700
Data Index: 6926823 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.7975. Min Act: -0.1700
Data Index: 5629565 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.7975. Min Act: -0.1700
Data Index: 812681 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.8134. Min Act: -0.1700
Data Index: 1322368 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.7975. Min Act: -0.1700
Data Index: 3051352 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.7975. Min Act: -0.1700
Data Index: 2559705 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9721. Min Range: -2.9721
Max Act: 2.7975. Min Act: -0.1700
Data Index: 146030 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #19