Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3487 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1439. Min Range: -6.1439
Max Act: 6.1439. Min Act: -0.1700
Data Index: 3577784 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1439. Min Range: -6.1439
Max Act: 6.1126. Min Act: -0.1700
Data Index: 5006884 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1439. Min Range: -6.1439
Max Act: 6.0814. Min Act: -0.1700
Data Index: 4893850 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1439. Min Range: -6.1439
Max Act: 6.0501. Min Act: -0.1700
Data Index: 5307763 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1439. Min Range: -6.1439
Max Act: 6.0189. Min Act: -0.1700
Data Index: 8182955 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9876. Min Act: -0.1700
Data Index: 6508724 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9876. Min Act: -0.1700
Data Index: 7992017 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9564. Min Act: -0.1700
Data Index: 3842873 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9564. Min Act: -0.1700
Data Index: 941261 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9876. Min Act: -0.1700
Data Index: 2086751 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9876. Min Act: -0.1700
Data Index: 4651537 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9564. Min Act: -0.1700
Data Index: 2675922 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9564. Min Act: -0.1700
Data Index: 2828584 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9564. Min Act: -0.1700
Data Index: 2685562 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9251. Min Act: -0.1700
Data Index: 3367423 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.8939. Min Act: -0.1700
Data Index: 4659416 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9251. Min Act: -0.1700
Data Index: 819093 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.8939. Min Act: -0.1700
Data Index: 4025847 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.8626. Min Act: -0.1700
Data Index: 980853 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1439. Min Range: -6.1439
Max Act: 5.9251. Min Act: -0.1700
Data Index: 4180631 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19